Controllable single- or two-speaker speech generation
<!doctype html> <html lang="zh-TW-x-mtfrom-en" dir="ltr"> <head> <meta name="google-signin-client-id" content="721724668570-nbkv1cfusk7kk4eni4pjvepaus73b13t.apps.googleusercontent.com"><meta name="google-signin-scope" content="profile email https://www.googleapis.com/auth/developerprofiles https://www.googleapis.com/auth/developerprofiles.award https://www.googleapis.com/auth/devprofiles.full_control.firstparty"><meta property="og:site_name" content="Google Cloud Documentation"> <meta property="og:type" content="website"><meta name="theme-color" content="#1a73e8"><meta charset="utf-8"> <meta content="IE=Edge" http-equiv="X-UA-Compatible"> <meta name="viewport" content="width=device-width, initial-scale=1"> <link rel="manifest" href="/_pwa/clouddocs/manifest.json" crossorigin="use-credentials"> <link rel="preconnect" href="//www.gstatic.com" crossorigin> <link rel="preconnect" href="//fonts.googleapis.com" crossorigin> <link rel="preconnect" href="//www.google-analytics.com" crossorigin><link rel="stylesheet" href="//fonts.googleapis.com/css?family=Google+Sans:400,500|Roboto:400,400italic,500,500italic,700,700italic|Roboto+Mono:400,500,700&display=swap"> <link rel="stylesheet" href="//fonts.googleapis.com/css2?family=Material+Icons&family=Material+Symbols+Outlined&display=block"><link rel="stylesheet" href="https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/clouddocs/css/app.css"> <link rel="stylesheet" href="https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/clouddocs/css/dark-theme.css" disabled> <link rel="shortcut icon" href="https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/clouddocs/images/favicons/onecloud/favicon.ico"> <link rel="apple-touch-icon" href="https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/clouddocs/images/favicons/onecloud/super_cloud.png"><link rel="canonical" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=zh-tw"><link rel="search" type="application/opensearchdescription+xml" title="Google Cloud Documentation" href="https://docs.cloud.google.com/s/opensearch.xml?hl=zh-tw"> <link rel="alternate" hreflang="en" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts" /><link rel="alternate" hreflang="x-default" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts" /><link rel="alternate" hreflang="zh-Hans" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=zh-cn" /><link rel="alternate" hreflang="zh-Hant" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=zh-tw" /><link rel="alternate" hreflang="fr" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=fr" /><link rel="alternate" hreflang="de" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=de" /><link rel="alternate" hreflang="he" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=he" /><link rel="alternate" hreflang="id" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=id" /><link rel="alternate" hreflang="it" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=it" /><link rel="alternate" hreflang="ja" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=ja" /><link rel="alternate" hreflang="ko" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=ko" /><link rel="alternate" hreflang="pt-BR" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=pt-br" /><link rel="alternate" hreflang="pt" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=pt" /><link rel="alternate" hreflang="es" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=es" /><link rel="alternate" hreflang="es-419" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=es-419" /><link rel="alternate" hreflang="en-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts" /><link rel="alternate" hreflang="x-default" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts" /><link rel="alternate" hreflang="zh-Hans-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=zh-cn" /><link rel="alternate" hreflang="zh-Hant-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=zh-tw" /><link rel="alternate" hreflang="fr-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=fr" /><link rel="alternate" hreflang="de-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=de" /><link rel="alternate" hreflang="he-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=he" /><link rel="alternate" hreflang="id-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=id" /><link rel="alternate" hreflang="it-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=it" /><link rel="alternate" hreflang="ja-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=ja" /><link rel="alternate" hreflang="ko-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=ko" /><link rel="alternate" hreflang="pt-BR-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=pt-br" /><link rel="alternate" hreflang="pt-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=pt" /><link rel="alternate" hreflang="es-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=es" /><link rel="alternate" hreflang="es-419-cn" href="https://docs.cloud.google.cn/text-to-speech/docs/gemini-tts?hl=es-419" /><title>Gemini-TTS | Cloud Text-to-Speech | Google Cloud Documentation</title> <meta property="og:title" content="Gemini-TTS | Cloud Text-to-Speech | Google Cloud Documentation"><meta property="og:url" content="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=zh-tw"><meta property="og:image" content="https://docs.cloud.google.com/_static/cloud/images/social-icon-google-cloud-1200-630.png?hl=zh-tw"> <meta property="og:image:width" content="1200"> <meta property="og:image:height" content="630"><meta property="og:locale" content="zh_tw"><meta name="twitter:card" content="summary_large_image"><script type="application/ld+json"> { "@context": "https://schema.org", "@type": "Article", "headline": "Gemini-TTS" } </script><script type="application/ld+json"> { "@context": "https://schema.org", "@type": "BreadcrumbList", "itemListElement": [{ "@type": "ListItem", "position": 1, "name": "Cloud Text-to-Speech", "item": "https://docs.cloud.google.com/text-to-speech/docs" },{ "@type": "ListItem", "position": 2, "name": "Gemini-TTS", "item": "https://docs.cloud.google.com/text-to-speech/docs/gemini-tts" }] } </script><link rel="alternate machine-translated-from" hreflang="en" href="https://docs.cloud.google.com/text-to-speech/docs/gemini-tts?hl=en"> </head> <body class="color-scheme--light" template="page" theme="clouddocs-theme" type="article" appearance layout="docs" free-trial display-toc pending> <devsite-progress type="indeterminate" id="app-progress"></devsite-progress> <a href="#main-content" class="skip-link button"> 跳至主要內容 </a> <section class="devsite-wrapper"> <devsite-cookie-notification-bar></devsite-cookie-notification-bar> <cloudx-track userCountry="US"></cloudx-track> <devsite-header role="banner" keep-tabs-visible> <div class="devsite-header--inner" data-nosnippet> <div class="devsite-top-logo-row-wrapper-wrapper"> <div class="devsite-top-logo-row-wrapper"> <div class="devsite-top-logo-row"> <button type="button" id="devsite-hamburger-menu" class="devsite-header-icon-button button-flat material-icons gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Navigation menu button" visually-hidden aria-label="開啟選單"> </button> <div class="devsite-product-name-wrapper"> <a href="/" class="devsite-site-logo-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Site logo" track-type="globalNav" track-name="googleCloudDocumentation" track-metadata-position="nav" track-metadata-eventDetail="nav"> <picture> <source srcset="https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/clouddocs/images/lockup_dark_theme.svg" media="(prefers-color-scheme: dark)" class="devsite-dark-theme"> <img src="https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/clouddocs/images/lockup_full_color.svg" class="devsite-site-logo" alt="Google Cloud Documentation"> </picture> </a> </div> <div class="devsite-top-logo-row-middle"> <div class="devsite-header-upper-tabs"> <devsite-tabs class="upper-tabs"> <nav class="devsite-tabs-wrapper" aria-label="上層分頁"> <tab class="devsite-dropdown devsite-active devsite-clickable "> <a href="https://docs.cloud.google.com/docs?hl=zh-tw" class="devsite-tabs-content gc-analytics-event " track-metadata-eventdetail="https://docs.cloud.google.com/docs?hl=zh-tw" track-type="nav" track-metadata-position="nav - docs-home" track-metadata-module="primary nav" aria-label="技術領域, selected" data-category="Site-Wide Custom Events" data-label="Tab: 技術領域" track-name="docs-home" track-link-column-type="single-column" > 技術領域 </a> <button aria-haspopup="menu" aria-expanded="false" aria-label="以下項目的下拉式選單: 技術領域" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="primary nav" data-category="Site-Wide Custom Events" data-label="Tab: 技術領域" track-name="docs-home" track-link-column-type="single-column" class="devsite-tabs-dropdown-toggle devsite-icon devsite-icon-arrow-drop-down"></button> <div class="devsite-tabs-dropdown" role="menu" aria-label="submenu" hidden> <div class="devsite-tabs-dropdown-content"> <button class="devsite-tabs-close-button material-icons button-flat gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Close dropdown menu" aria-label="關閉下拉式選單" track-type="nav" track-name="close" track-metadata-eventdetail="#" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav">close</button> <div class="devsite-tabs-dropdown-column "> <ul class="devsite-tabs-dropdown-section "> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/ai-ml?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/ai-ml?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> AI 和機器學習 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/application-development?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/application-development?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 應用程式開發 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/application-hosting?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/application-hosting?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 應用程式託管 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/compute-area?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/compute-area?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 運算 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/data?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/data?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 資料分析和管道 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/databases?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/databases?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 資料庫 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/dhm-cloud?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/dhm-cloud?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 分散式雲端、混合雲與多雲端 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/generative-ai?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/generative-ai?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 生成式 AI </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/industry?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/industry?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 產業解決方案 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/networking?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/networking?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 網路 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/observability?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/observability?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 觀測能力與監控 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/security?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/security?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 安全性 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/storage?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/storage?hl=zh-tw" track-metadata-position="nav - docs-home" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> Storage </div> </a> </li> </ul> </div> </div> </div> </tab> <tab class="devsite-dropdown devsite-clickable "> <a href="https://docs.cloud.google.com/docs/cross-product-overviews?hl=zh-tw" class="devsite-tabs-content gc-analytics-event " track-metadata-eventdetail="https://docs.cloud.google.com/docs/cross-product-overviews?hl=zh-tw" track-type="nav" track-metadata-position="nav - crossproduct" track-metadata-module="primary nav" data-category="Site-Wide Custom Events" data-label="Tab: 跨產品工具" track-name="crossproduct" track-link-column-type="single-column" > 跨產品工具 </a> <button aria-haspopup="menu" aria-expanded="false" aria-label="以下項目的下拉式選單: 跨產品工具" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/cross-product-overviews?hl=zh-tw" track-metadata-position="nav - crossproduct" track-metadata-module="primary nav" data-category="Site-Wide Custom Events" data-label="Tab: 跨產品工具" track-name="crossproduct" track-link-column-type="single-column" class="devsite-tabs-dropdown-toggle devsite-icon devsite-icon-arrow-drop-down"></button> <div class="devsite-tabs-dropdown" role="menu" aria-label="submenu" hidden> <div class="devsite-tabs-dropdown-content"> <button class="devsite-tabs-close-button material-icons button-flat gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Close dropdown menu" aria-label="關閉下拉式選單" track-type="nav" track-name="close" track-metadata-eventdetail="#" track-metadata-position="nav - crossproduct" track-metadata-module="tertiary nav">close</button> <div class="devsite-tabs-dropdown-column "> <ul class="devsite-tabs-dropdown-section "> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/access-resources?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/access-resources?hl=zh-tw" track-metadata-position="nav - crossproduct" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 存取權和資源管理 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/costs-usage?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/costs-usage?hl=zh-tw" track-metadata-position="nav - crossproduct" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 成本和用量管理 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/iac?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/iac?hl=zh-tw" track-metadata-position="nav - crossproduct" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 基礎架構即程式碼 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/migration?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/migration?hl=zh-tw" track-metadata-position="nav - crossproduct" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> 遷移 </div> </a> </li> <li class="devsite-nav-item"> <a href="https://docs.cloud.google.com/docs/devtools?hl=zh-tw" track-type="nav" track-metadata-eventdetail="https://docs.cloud.google.com/docs/devtools?hl=zh-tw" track-metadata-position="nav - crossproduct" track-metadata-module="tertiary nav" tooltip > <div class="devsite-nav-item-title"> SDK、語言、框架和工具 </div> </a> </li> </ul> </div> </div> </div> </tab> </nav> </devsite-tabs> </div> <devsite-search enable-signin enable-search enable-suggestions enable-search-summaries project-name="Cloud Text-to-Speech" tenant-name="Google Cloud Documentation" project-scope="/text-to-speech/docs" url-scoped="https://docs.cloud.google.com/s/results/text-to-speech/docs?hl=zh-tw" > <form class="devsite-search-form" action="https://docs.cloud.google.com/s/results?hl=zh-tw" method="GET"> <div class="devsite-search-container"> <button type="button" search-open class="devsite-search-button devsite-header-icon-button button-flat material-icons" aria-label="開啟搜尋"></button> <div class="devsite-searchbox"> <input aria-activedescendant="" aria-autocomplete="list" aria-label="搜尋結果" aria-expanded="false" aria-haspopup="listbox" autocomplete="off" class="devsite-search-field devsite-search-query" name="q" placeholder="搜尋結果" role="combobox" type="text" value="" > <div class="devsite-search-image material-icons" aria-hidden="true"> <svg class="devsite-search-ai-image" width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"> <g clip-path="url(#clip0_6641_386)"> <path d="M19.6 21L13.3 14.7C12.8 15.1 12.225 15.4167 11.575 15.65C10.925 15.8833 10.2333 16 9.5 16C7.68333 16 6.14167 15.375 4.875 14.125C3.625 12.8583 3 11.3167 3 9.5C3 7.68333 3.625 6.15 4.875 4.9C6.14167 3.63333 7.68333 3 9.5 3C10.0167 3 10.5167 3.05833 11 3.175C11.4833 3.275 11.9417 3.43333 12.375 3.65L10.825 5.2C10.6083 5.13333 10.3917 5.08333 10.175 5.05C9.95833 5.01667 9.73333 5 9.5 5C8.25 5 7.18333 5.44167 6.3 6.325C5.43333 7.19167 5 8.25 5 9.5C5 10.75 5.43333 11.8167 6.3 12.7C7.18333 13.5667 8.25 14 9.5 14C10.6667 14 11.6667 13.625 12.5 12.875C13.35 12.1083 13.8417 11.15 13.975 10H15.975C15.925 10.6333 15.7833 11.2333 15.55 11.8C15.3333 12.3667 15.05 12.8667 14.7 13.3L21 19.6L19.6 21ZM17.5 12C17.5 10.4667 16.9667 9.16667 15.9 8.1C14.8333 7.03333 13.5333 6.5 12 6.5C13.5333 6.5 14.8333 5.96667 15.9 4.9C16.9667 3.83333 17.5 2.53333 17.5 0.999999C17.5 2.53333 18.0333 3.83333 19.1 4.9C20.1667 5.96667 21.4667 6.5 23 6.5C21.4667 6.5 20.1667 7.03333 19.1 8.1C18.0333 9.16667 17.5 10.4667 17.5 12Z" fill="#5F6368"/> </g> <defs> <clipPath id="clip0_6641_386"> <rect width="24" height="24" fill="white"/> </clipPath> </defs> </svg> </div> <div class="devsite-search-shortcut-icon-container" aria-hidden="true"> <kbd class="devsite-search-shortcut-icon">/</kbd> </div> </div> </div> </form> <button type="button" search-close class="devsite-search-button devsite-header-icon-button button-flat material-icons" aria-label="關閉搜尋"></button> </devsite-search> </div> <a class="devsite-header-link devsite-top-button button gc-analytics-event button-with-icon" href="//console.cloud.google.com/?hl=zh-tw" data-category="Site-Wide Custom Events" data-label="Site header link: 控制台" track-name="console" track-type="globalNav" track-metadata-eventDetail="nav" referrerpolicy="no-referrer-when-downgrade" track-metadata-position="nav" > 控制台 </a> <devsite-appearance-selector></devsite-appearance-selector> <devsite-language-selector> <ul role="presentation"> <li role="presentation"> <a role="menuitem" lang="en" >English</a> </li> <li role="presentation"> <a role="menuitem" lang="de" >Deutsch</a> </li> <li role="presentation"> <a role="menuitem" lang="es" >Español</a> </li> <li role="presentation"> <a role="menuitem" lang="es_419" >Español – América Latina</a> </li> <li role="presentation"> <a role="menuitem" lang="fr" >Français</a> </li> <li role="presentation"> <a role="menuitem" lang="id" >Indonesia</a> </li> <li role="presentation"> <a role="menuitem" lang="it" >Italiano</a> </li> <li role="presentation"> <a role="menuitem" lang="pt" >Português</a> </li> <li role="presentation"> <a role="menuitem" lang="pt_br" >Português – Brasil</a> </li> <li role="presentation"> <a role="menuitem" lang="he" >עברית</a> </li> <li role="presentation"> <a role="menuitem" lang="zh_cn" >中文 – 简体</a> </li> <li role="presentation"> <a role="menuitem" lang="zh_tw" >中文 – 繁體</a> </li> <li role="presentation"> <a role="menuitem" lang="ja" >日本語</a> </li> <li role="presentation"> <a role="menuitem" lang="ko" >한국어</a> </li> </ul> </devsite-language-selector> <devsite-user enable-profiles fp-auth id="devsite-user"> <span class="button devsite-top-button" aria-hidden="true" visually-hidden>登入</span> </devsite-user> </div> </div> </div> <div class="devsite-collapsible-section "> <div class="devsite-header-background"> <div class="devsite-product-id-row" > <div class="devsite-product-description-row"> <div class="devsite-product-id"> <a href="https://docs.cloud.google.com/text-to-speech/docs?hl=zh-tw"> <div class="devsite-product-logo-container" size="medium" > <picture> <source class="devsite-dark-theme" media="(prefers-color-scheme: dark)" srcset=" /_static/clouddocs/images/icons/categories/ai-and-machine-learning-white.svg" sizes="64px"> <img class="devsite-product-logo" alt="" src="https://docs.cloud.google.com/_static/clouddocs/images/icons/categories/ai-and-machine-learning-color.svg?hl=zh-tw" srcset=" /_static/clouddocs/images/icons/categories/ai-and-machine-learning-color.svg" sizes="64px" loading="lazy" > </picture> </div> </a> <ul class="devsite-breadcrumb-list" > <li class="devsite-breadcrumb-item "> <a href="https://docs.cloud.google.com/text-to-speech/docs?hl=zh-tw" class="devsite-breadcrumb-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Lower Header" data-value="1" track-type="globalNav" track-name="breadcrumb" track-metadata-position="1" track-metadata-eventdetail="Cloud Text-to-Speech" > Cloud Text-to-Speech </a> </li> </ul> </div> </div> <div class="devsite-product-button-row"> <a href="//console.cloud.google.com/freetrial?hl=zh-tw" class="cloud-free-trial-button button button-primary " track-metadata-position="nav" referrerpolicy="no-referrer-when-downgrade" track-name="gcpCta" track-type="freeTrial" track-metadata-eventDetail="nav" >免費試用</a> </div> </div> <div class="devsite-doc-set-nav-row"> <devsite-tabs class="lower-tabs"> <nav class="devsite-tabs-wrapper" aria-label="下層分頁"> <tab class="devsite-active"> <a href="https://docs.cloud.google.com/text-to-speech/docs/create-audio-text-client-libraries?hl=zh-tw" class="devsite-tabs-content gc-analytics-event " track-metadata-eventdetail="https://docs.cloud.google.com/text-to-speech/docs/create-audio-text-client-libraries?hl=zh-tw" track-type="nav" track-metadata-position="nav - 指南" track-metadata-module="primary nav" aria-label="指南, selected" data-category="Site-Wide Custom Events" data-label="Tab: 指南" track-name="指南" > 指南 </a> </tab> <tab > <a href="https://docs.cloud.google.com/text-to-speech/docs/apis?hl=zh-tw" class="devsite-tabs-content gc-analytics-event " track-metadata-eventdetail="https://docs.cloud.google.com/text-to-speech/docs/apis?hl=zh-tw" track-type="nav" track-metadata-position="nav - 參考資料" track-metadata-module="primary nav" data-category="Site-Wide Custom Events" data-label="Tab: 參考資料" track-name="參考資料" > 參考資料 </a> </tab> <tab > <a href="https://docs.cloud.google.com/text-to-speech/docs/samples?hl=zh-tw" class="devsite-tabs-content gc-analytics-event " track-metadata-eventdetail="https://docs.cloud.google.com/text-to-speech/docs/samples?hl=zh-tw" track-type="nav" track-metadata-position="nav - 範例" track-metadata-module="primary nav" data-category="Site-Wide Custom Events" data-label="Tab: 範例" track-name="範例" > 範例 </a> </tab> <tab > <a href="https://docs.cloud.google.com/text-to-speech/docs/support?hl=zh-tw" class="devsite-tabs-content gc-analytics-event " track-metadata-eventdetail="https://docs.cloud.google.com/text-to-speech/docs/support?hl=zh-tw" track-type="nav" track-metadata-position="nav - 支援" track-metadata-module="primary nav" data-category="Site-Wide Custom Events" data-label="Tab: 支援" track-name="支援" > 支援 </a> </tab> <tab > <a href="https://docs.cloud.google.com/text-to-speech/docs/resources?hl=zh-tw" class="devsite-tabs-content gc-analytics-event " track-metadata-eventdetail="https://docs.cloud.google.com/text-to-speech/docs/resources?hl=zh-tw" track-type="nav" track-metadata-position="nav - 資源" track-metadata-module="primary nav" data-category="Site-Wide Custom Events" data-label="Tab: 資源" track-name="資源" > 資源 </a> </tab> <tab > <a href="https://cloud.google.com/text-to-speech/pricing?hl=zh-tw" class="devsite-tabs-content gc-analytics-event " track-metadata-eventdetail="https://cloud.google.com/text-to-speech/pricing?hl=zh-tw" track-type="nav" track-metadata-position="nav - 定價" track-metadata-module="primary nav" data-category="Site-Wide Custom Events" data-label="Tab: 定價" track-name="定價" > 定價 </a> </tab> <tab > <a href="https://docs.cloud.google.com/text-to-speech/docs/release-notes?hl=zh-tw" class="devsite-tabs-content gc-analytics-event " track-metadata-eventdetail="https://docs.cloud.google.com/text-to-speech/docs/release-notes?hl=zh-tw" track-type="nav" track-metadata-position="nav - 版本資訊" track-metadata-module="primary nav" data-category="Site-Wide Custom Events" data-label="Tab: 版本資訊" track-name="版本資訊" > 版本資訊 </a> </tab> </nav> </devsite-tabs> </div> </div> </div> </div> </devsite-header> <devsite-book-nav scrollbars > <div class="devsite-book-nav-filter" > <span class="filter-list-icon material-icons" aria-hidden="true"></span> <input type="text" placeholder="篩選器" aria-label="篩選類型" role="searchbox"> <span class="filter-clear-button hidden" data-title="清除篩選器" aria-label="清除篩選器" role="button" tabindex="0"></span> </div> <nav class="devsite-book-nav devsite-nav nocontent" data-nosnippet aria-label="側邊選單"> <div class="devsite-mobile-header"> <button type="button" id="devsite-close-nav" class="devsite-header-icon-button button-flat material-icons gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Close navigation" aria-label="關閉導覽列"> </button> <div class="devsite-product-name-wrapper"> <a href="/" class="devsite-site-logo-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Site logo" track-type="globalNav" track-name="googleCloudDocumentation" track-metadata-position="nav" track-metadata-eventDetail="nav"> <picture> <source srcset="https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/clouddocs/images/lockup_dark_theme.svg" media="(prefers-color-scheme: dark)" class="devsite-dark-theme"> <img src="https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/clouddocs/images/lockup_full_color.svg" class="devsite-site-logo" alt="Google Cloud Documentation"> </picture> </a> </div> </div> <div class="devsite-book-nav-wrapper"> <div class="devsite-mobile-nav-top"> <ul class="devsite-nav-list"> <li class="devsite-nav-item"> <a href="/docs" class="devsite-nav-title gc-analytics-event devsite-nav-active" data-category="Site-Wide Custom Events" data-label="Tab: 技術領域" track-name="docs-home" track-link-column-type="single-column" data-category="Site-Wide Custom Events" data-label="Responsive Tab: 技術領域" track-type="globalNav" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 技術領域 </span> </a> <ul class="devsite-nav-responsive-tabs devsite-nav-has-menu "> <li class="devsite-nav-item"> <span class="devsite-nav-title" tooltip data-category="Site-Wide Custom Events" data-label="Tab: 技術領域" track-name="docs-home" track-link-column-type="single-column" > <span class="devsite-nav-text" tooltip menu="技術領域"> 更多 </span> <span class="devsite-nav-icon material-icons" data-icon="forward" menu="技術領域"> </span> </span> </li> </ul> <ul class="devsite-nav-responsive-tabs"> <li class="devsite-nav-item"> <a href="/text-to-speech/docs/create-audio-text-client-libraries" class="devsite-nav-title gc-analytics-event devsite-nav-active" data-category="Site-Wide Custom Events" data-label="Tab: 指南" track-name="指南" data-category="Site-Wide Custom Events" data-label="Responsive Tab: 指南" track-type="globalNav" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip menu="_book"> 指南 </span> </a> </li> <li class="devsite-nav-item"> <a href="/text-to-speech/docs/apis" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Tab: 參考資料" track-name="參考資料" data-category="Site-Wide Custom Events" data-label="Responsive Tab: 參考資料" track-type="globalNav" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 參考資料 </span> </a> </li> <li class="devsite-nav-item"> <a href="/text-to-speech/docs/samples" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Tab: 範例" track-name="範例" data-category="Site-Wide Custom Events" data-label="Responsive Tab: 範例" track-type="globalNav" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 範例 </span> </a> </li> <li class="devsite-nav-item"> <a href="/text-to-speech/docs/support" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Tab: 支援" track-name="支援" data-category="Site-Wide Custom Events" data-label="Responsive Tab: 支援" track-type="globalNav" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 支援 </span> </a> </li> <li class="devsite-nav-item"> <a href="/text-to-speech/docs/resources" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Tab: 資源" track-name="資源" data-category="Site-Wide Custom Events" data-label="Responsive Tab: 資源" track-type="globalNav" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 資源 </span> </a> </li> <li class="devsite-nav-item"> <a href="https://cloud.google.com/text-to-speech/pricing" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Tab: 定價" track-name="定價" data-category="Site-Wide Custom Events" data-label="Responsive Tab: 定價" track-type="globalNav" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 定價 </span> </a> </li> <li class="devsite-nav-item"> <a href="/text-to-speech/docs/release-notes" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Tab: 版本資訊" track-name="版本資訊" data-category="Site-Wide Custom Events" data-label="Responsive Tab: 版本資訊" track-type="globalNav" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 版本資訊 </span> </a> </li> </ul> </li> <li class="devsite-nav-item"> <a href="/docs/cross-product-overviews" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Tab: 跨產品工具" track-name="crossproduct" track-link-column-type="single-column" data-category="Site-Wide Custom Events" data-label="Responsive Tab: 跨產品工具" track-type="globalNav" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 跨產品工具 </span> </a> <ul class="devsite-nav-responsive-tabs devsite-nav-has-menu "> <li class="devsite-nav-item"> <span class="devsite-nav-title" tooltip data-category="Site-Wide Custom Events" data-label="Tab: 跨產品工具" track-name="crossproduct" track-link-column-type="single-column" > <span class="devsite-nav-text" tooltip menu="跨產品工具"> 更多 </span> <span class="devsite-nav-icon material-icons" data-icon="forward" menu="跨產品工具"> </span> </span> </li> </ul> </li> <li class="devsite-nav-item"> <a href="//console.cloud.google.com/" class="devsite-nav-title gc-analytics-event button-with-icon" track-name="console" track-type="globalNav" track-metadata-eventDetail="nav" referrerpolicy="no-referrer-when-downgrade" track-metadata-position="nav" data-category="Site-Wide Custom Events" data-label="Responsive Tab: 控制台" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 控制台 </span> </a> </li> </ul> </div> <div class="devsite-mobile-nav-bottom"> <ul class="devsite-nav-list" menu="_book"> <li class="devsite-nav-item"><a href="/text-to-speech/docs" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>Cloud Text-to-Speech</span></a></li> <li class="devsite-nav-item devsite-nav-heading"><div class="devsite-nav-title devsite-nav-title-no-path"> <span class="devsite-nav-text" tooltip>模型</span> </div></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/gemini-tts" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>Gemini-TTS</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/chirp3-hd" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>Chirp 3:HD 語音</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/chirp3-instant-custom-voice" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>Chirp 3:即時 Custom Voice</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/list-voices-and-types" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>語言和語音支援服務</span></a></li> <li class="devsite-nav-item devsite-nav-heading"><div class="devsite-nav-title devsite-nav-title-no-path"> <span class="devsite-nav-text" tooltip>快速入門導覽課程</span> </div></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/quickstarts" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>所有快速入門導覽課程</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/create-audio-text-client-libraries" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>使用用戶端程式庫</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/create-audio-text-command-line" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>使用指令列</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/create-audio-text-console" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>使用控制台</span></a></li> <li class="devsite-nav-item devsite-nav-heading"><div class="devsite-nav-title devsite-nav-title-no-path"> <span class="devsite-nav-text" tooltip>使用指南</span> </div></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/how-to" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>所有使用指南</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/before-you-begin" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>事前準備</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/create-audio-text-long-audio-synthesis" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>長音訊合成</span></a></li> <li class="devsite-nav-item devsite-nav-preview"><a href="/text-to-speech/docs/create-audio-text-streaming" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>雙向串流合成</span><span class="devsite-nav-icon material-icons" data-icon="preview" data-title="預覽" aria-hidden="true"></span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/audio-profiles" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>使用裝置設定檔</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/create-audio" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>建立語音音訊檔案</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/ssml-tutorial" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>使用 SSML 朗讀地址</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/samples" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>所有 Text-to-Speech 程式碼範例</span></a></li> <li class="devsite-nav-item devsite-nav-heading"><div class="devsite-nav-title devsite-nav-title-no-path"> <span class="devsite-nav-text" tooltip>概念</span> </div></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/basics" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>基本概念</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/endpoints" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>區域規劃</span></a></li> <li class="devsite-nav-item devsite-nav-heading"><div class="devsite-nav-title devsite-nav-title-no-path"> <span class="devsite-nav-text" tooltip>資源</span> </div></li> <li class="devsite-nav-item"><a href="/text-to-speech/quotas" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>配額與限制</span></a></li> <li class="devsite-nav-item"><a href="https://cloud.google.com/text-to-speech/sla" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>服務水準協議</span></a></li> <li class="devsite-nav-item"><a href="/text-to-speech/docs/data-logging" class="devsite-nav-title" ><span class="devsite-nav-text" tooltip>資料記錄</span></a></li> </ul> <ul class="devsite-nav-list" menu="技術領域" aria-label="側邊選單" hidden> <li class="devsite-nav-item"> <a href="/docs/ai-ml" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: AI 和機器學習" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > AI 和機器學習 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/application-development" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 應用程式開發" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 應用程式開發 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/application-hosting" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 應用程式託管" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 應用程式託管 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/compute-area" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 運算" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 運算 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/data" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 資料分析和管道" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 資料分析和管道 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/databases" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 資料庫" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 資料庫 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/dhm-cloud" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 分散式雲端、混合雲與多雲端" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 分散式雲端、混合雲與多雲端 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/generative-ai" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 生成式 AI" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 生成式 AI </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/industry" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 產業解決方案" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 產業解決方案 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/networking" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 網路" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 網路 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/observability" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 觀測能力與監控" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 觀測能力與監控 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/security" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 安全性" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 安全性 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/storage" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: Storage" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > Storage </span> </a> </li> </ul> <ul class="devsite-nav-list" menu="跨產品工具" aria-label="側邊選單" hidden> <li class="devsite-nav-item"> <a href="/docs/access-resources" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 存取權和資源管理" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 存取權和資源管理 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/costs-usage" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 成本和用量管理" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 成本和用量管理 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/iac" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 基礎架構即程式碼" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 基礎架構即程式碼 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/migration" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: 遷移" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > 遷移 </span> </a> </li> <li class="devsite-nav-item"> <a href="/docs/devtools" class="devsite-nav-title gc-analytics-event " data-category="Site-Wide Custom Events" data-label="Responsive Tab: SDK、語言、框架和工具" track-type="navMenu" track-metadata-eventDetail="globalMenu" track-metadata-position="nav"> <span class="devsite-nav-text" tooltip > SDK、語言、框架和工具 </span> </a> </li> </ul> </div> </div> </nav> </devsite-book-nav> <section id="gc-wrapper"> <main role="main" id="main-content" class="devsite-main-content" has-book-nav has-sidebar > <div class="devsite-sidebar"> <div class="devsite-sidebar-content"> <devsite-toc class="devsite-nav" role="navigation" aria-label="這個頁面中的內容" depth="2" scrollbars data-nosnippet ></devsite-toc> <devsite-recommendations-sidebar class="nocontent devsite-nav" data-nosnippet> </devsite-recommendations-sidebar> </div> </div> <devsite-content> <article class="devsite-article"> <div class="devsite-article-meta nocontent" role="navigation" data-nosnippet> <ul class="devsite-breadcrumb-list" aria-label="導覽標記"> <li class="devsite-breadcrumb-item "> <a href="https://docs.cloud.google.com/?hl=zh-tw" class="devsite-breadcrumb-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Breadcrumbs" data-value="1" track-type="globalNav" track-name="breadcrumb" track-metadata-position="1" track-metadata-eventdetail="Google Cloud Documentation" > Home </a> </li> <li class="devsite-breadcrumb-item "> <div class="devsite-breadcrumb-guillemet material-icons" aria-hidden="true"></div> <a href="https://docs.cloud.google.com/docs?hl=zh-tw" class="devsite-breadcrumb-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Breadcrumbs" data-value="2" track-type="globalNav" track-name="breadcrumb" track-metadata-position="2" track-metadata-eventdetail="Documentation" > Documentation </a> </li> <li class="devsite-breadcrumb-item "> <div class="devsite-breadcrumb-guillemet material-icons" aria-hidden="true"></div> <a href="https://docs.cloud.google.com/docs/ai-ml?hl=zh-tw" class="devsite-breadcrumb-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Breadcrumbs" data-value="3" track-type="globalNav" track-name="breadcrumb" track-metadata-position="3" track-metadata-eventdetail="AI and ML" > AI and ML </a> </li> <li class="devsite-breadcrumb-item "> <div class="devsite-breadcrumb-guillemet material-icons" aria-hidden="true"></div> <a href="https://docs.cloud.google.com/text-to-speech/docs?hl=zh-tw" class="devsite-breadcrumb-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Breadcrumbs" data-value="4" track-type="globalNav" track-name="breadcrumb" track-metadata-position="4" track-metadata-eventdetail="Cloud Text-to-Speech" > Cloud Text-to-Speech </a> </li> <li class="devsite-breadcrumb-item "> <div class="devsite-breadcrumb-guillemet material-icons" aria-hidden="true"></div> <a href="https://docs.cloud.google.com/text-to-speech/docs/create-audio-text-client-libraries?hl=zh-tw" class="devsite-breadcrumb-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Breadcrumbs" data-value="5" track-type="globalNav" track-name="breadcrumb" track-metadata-position="5" track-metadata-eventdetail="" > 指南 </a> </li> </ul> <devsite-thumb-rating position="header"> </devsite-thumb-rating> </div> <devsite-feedback position="header" project-name="Cloud Text-to-Speech" product-id="5041938" bucket="Documentation" context="Cloud Text-to-Speech API docs feedback link" version="t-devsite-webserver-20260825-r00-rc00.479916215390653058" data-label="Send Feedback Button" track-type="feedback" track-name="sendFeedbackLink" track-metadata-position="header" class="nocontent" data-nosnippet project-feedback-url="https://issuetracker.google.com/issues/new?component=451645" project-icon="https://docs.cloud.google.com/_static/clouddocs/images/icons/categories/ai-and-machine-learning-color.svg?hl=zh-tw" project-support-url="https://docs.cloud.google.com/text-to-speech/docs/support?hl=zh-tw" > <button> 提供意見 </button> </devsite-feedback> <h1 class="devsite-page-title" tabindex="-1"> Gemini-TTS<devsite-actions hidden data-nosnippet><devsite-feature-tooltip ack-key="AckCollectionsBookmarkTooltipDismiss" analytics-category="Site-Wide Custom Events" analytics-action-show="Callout Profile displayed" analytics-action-close="Callout Profile dismissed" analytics-label="Create Collection Callout" class="devsite-page-bookmark-tooltip nocontent" data-nosnippet dismiss-button="true" id="devsite-collections-dropdown" dismiss-button-text="關閉" close-button-text="我知道了"> <devsite-bookmark></devsite-bookmark> <span slot="popout-heading"> 透過集合功能整理內容 </span> <span slot="popout-contents"> 你可以依據偏好儲存及分類內容。 </span> </devsite-feature-tooltip> <devsite-llm-tools></devsite-llm-tools></devsite-actions> </h1> <devsite-toc class="devsite-nav" depth="2" devsite-toc-embedded > </devsite-toc> <div class="devsite-article-body clearfix "> <section> <a class="button button-primary" href="https://console.cloud.google.com/vertex-ai/studio/media/generate;tab=audio?hl=zh-tw"target="console" track-name="consoleLink"> 在 Vertex AI Studio 中試用 Gemini-TTS</a> <a class="button" href="https://colab.research.google.com/github/GoogleCloudPlatform/generative-ai/blob/main/audio/speech/getting-started/get_started_with_gemini_tts_voices.ipynb?hl=zh-tw" ="" target="_blank" track-name="colabLink" track-type="notebookTutorial">在 Colab 中試用</a> <a class="button" href="https://github.com/GoogleCloudPlatform/generative-ai/blob/main/audio/speech/getting-started/get_started_with_gemini_tts_voices.ipynb" ="" target="_blank" track-name="gitHubLink" track-type="notebookTutorial">在 GitHub 中查看筆記本</a> </section> <p>Gemini-TTS 是最新推出的文字轉語音技術,不僅能生成自然聽感的語音,還可根據文字提示詞精細控制生成的音訊。有了 Gemini-TTS,無論是簡短文字片段還是長篇敘事,都能合成單人或多人語音,還可以透過自然語言提示詞精準指定風格、口音、語速、語氣,甚至是表達情緒。</p> <h2 data-text="可用模型" id="available_models" tabindex="-1">可用模型</h2> <p>Gemini-TTS 包含下列可用模型:</p> <div> <devsite-selector> <section> <h2 class="showalways" data-text="Gemini 2.5 Flash TTS" id="gemini-2-5-flash-tts" tabindex="-1">Gemini 2.5 Flash TTS</h2> <table> <tbody><tr> <th style="width:25%">模型 ID</th> <td><code dir="ltr" translate="no">gemini-2.5-flash-tts</code></td> </tr> <tr> <th>適合用途</th> <td>生成單一和多位說話者的文字轉語音音訊,延遲時間短、可控制,適用於日常應用程式,經濟實惠</td> </tr> <tr> <th>輸入和輸出模態</th> <td> <ul> <li><b>輸入內容</b>:文字</li> <li><b>輸出內容</b>:音訊</li> </ul> </td> </tr> <tr> <th>支援的說話者人數</th> <td>單一、多位說話者</td> </tr> <tr> <th>支援的輸出音訊格式<sup>*</sup></th> <td><code dir="ltr" translate="no">LINEAR16</code> (預設)、<code dir="ltr" translate="no">ALAW</code>、<code dir="ltr" translate="no">MULAW</code>、<code dir="ltr" translate="no">MP3</code>、<code dir="ltr" translate="no">OGG_OPUS</code>、<code dir="ltr" translate="no">PCM</code></td> </tr> <tr> <th>支援的區域</th> <td><code dir="ltr" translate="no">global</code></td> </tr> <tr> <th>語音選項</th> <td>查看<a href="#voice_options">語音選項</a></td> </tr> <tr> <th>支援的語言</th> <td>查看<a href="#available_languages">支援的語言</a></td> </tr> <tr> <th>範例</th> <td> <div></div><devsite-code><pre style="max-width:100%" translate="no" dir="ltr" is-upgraded> model: "gemini-2.5-flash-tts" prompt: "Say the following" text: "[extremely fast] Availability and terms may vary. Check our website or your local store for complete details and restrictions." speaker: "Kore" </pre></devsite-code> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/gemini-tts-flash-kore-fast.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> </tbody></table> </section> <section> <h2 class="showalways" data-text="Gemini 2.5 Pro TTS" id="gemini-2-5-pro-tts" tabindex="-1">Gemini 2.5 Pro TTS</h2> <table> <tbody><tr> <th style="width:25%">模型 ID</th> <td><code dir="ltr" translate="no">gemini-2.5-pro-tts</code></td> </tr> <tr> <th>適合用途</th> <td>高度控管結構化工作流程,例如生成 Podcast、有聲書、客戶服務等</td> </tr> <tr> <th>輸入和輸出模態</th> <td> <ul> <li><b>輸入內容</b>:文字</li> <li><b>輸出內容</b>:音訊</li> </ul> </td> </tr> <tr> <th>支援的說話者人數</th> <td>單一、多位說話者</td> </tr> <tr> <th>支援的輸出音訊格式<sup>*</sup></th> <td><code dir="ltr" translate="no">LINEAR16</code> (預設)、<code dir="ltr" translate="no">ALAW</code>、<code dir="ltr" translate="no">MULAW</code>、<code dir="ltr" translate="no">MP3</code>、<code dir="ltr" translate="no">OGG_OPUS</code>、<code dir="ltr" translate="no">PCM</code></td> </tr> <tr> <th>支援的區域</th> <td><code dir="ltr" translate="no">global</code></td> </tr> <tr> <th>語音選項</th> <td>查看<a href="#voice_options">語音選項</a></td> </tr> <tr> <th>支援的語言</th> <td>查看<a href="#available_languages">支援的語言</a></td> </tr> <tr> <th>範例</th> <td> <div></div><devsite-code><pre style="max-width:100%" translate="no" dir="ltr" is-upgraded> model: "gemini-2.5-pro-tts" prompt: "You are having a casual conversation with a friend. Say the following in a friendly and amused way." text: "hahah I did NOT expect that. Can you believe it!." speaker: "Callirrhoe" </pre></devsite-code> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/gemini-tts-pro-callirhoe-amused.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> </tbody></table> </section> </devsite-selector> </div> <p><sup>*</sup> 僅限 <code dir="ltr" translate="no">batch</code>。不支援 <code dir="ltr" translate="no">streaming</code>。</p> <h2 data-text="其他控制項" id="additional_controls" tabindex="-1">其他控制項</h2> <p>其他控制項和功能包括:</p> <ol> <li><p><strong>自然對話</strong>:語音互動品質極佳,表達方式和節奏模式更加自然,且延遲時間極短,對話流暢無礙。</p></li> <li><p><strong>風格控制</strong>:使用自然語言提示詞,即可在對話中調整語氣,讓對話採用特定口音,並產生各種語調和表達方式,包括輕聲耳語。</p></li> <li><p><strong>動態朗讀</strong>:這些模型能生動朗讀文字,例如詩歌、新聞報導和引人入勝的故事,還能依要求以特定情緒表演,或是模仿口音。</p></li> <li><p><strong>加強控制語速和發音</strong>:控制語速有助於確保發音更準確,包括讀出特定字詞。</p></li> </ol> <p>如要瞭解如何在應用程式中使用這些語音,請參閱「<a href="#use_gemini-tts">使用 Gemini-TTS</a>」。</p> <h2 data-text="語音選項" id="voice_options" tabindex="-1">語音選項</h2> <p>Gemini-TTS 提供多種語音選項,與現有的「Chirp 3:HD 語音」類似,但各有不同特色:</p> <div> <devsite-select column="0" id="filter-voices"> <select> <option>選取語音類型</option> <option value="unique-female-string">女性</option> <option value="unique-male-string">男性</option> </select> </devsite-select> <devsite-filter match="all" select-el-container-id="filter-voices"> <table> <thead> <tr> <th>名稱</th> <th>性別</th> <th>示範</th> </tr> </thead> <tbody class="list"> <tr> <!-- unique-female-string --> <td>Achernar</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-achernar.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Achird</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-achird.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Algenib</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-algenib.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Algieba</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-algieba.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Alnilam</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-alnilam.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Aoede</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-aoeda.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Autonoe</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-autonoe.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Callirrhoe</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-callirrhoe.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Charon</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-charon.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Despina</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-despina.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Enceladus</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-enceladus.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Erinome</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-erinome.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Fenrir</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-fenrir.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Gacrux</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-gacrux.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Iapetus</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-iapetus.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Kore</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-kore.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Laomedeia</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-laomedeia.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Leda</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-leda.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Orus</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-orus.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Pulcherrima</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-pulcherrima.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Puck</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-puck.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Rasalgethi</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-rasalgethi.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Sadachbia</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-sadachbia.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Sadaltager</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-sadaltager.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Schedar</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-schedar.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Sulafat</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-sulafat.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Umbriel</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-umbriel.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Vindemiatrix</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-vindemiatrix.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-female-string --> <td>Zephyr</td> <td>女性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-zephyr.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> <tr> <!-- unique-male-string --> <td>Zubenelgenubi</td> <td>男性</td> <td> <audio controls> <source src="https://docs.cloud.google.com/static/text-to-speech/docs/audio/chirp3-hd-zubenelgenubi.wav?hl=zh-tw" type="audio/wav" /> 您的瀏覽器不支援音訊元素。 </audio> </td> </tr> </tbody> </table> </devsite-filter> </div> <h2 data-text="支援的語言" id="available_languages" tabindex="-1">支援的語言</h2> <p>Gemini-TTS 支援下列語言:</p> <div> <devsite-select column="3" id="filter-languages"> <select> <option>選取推出階段</option> <option>正式發布版</option> <option>預先發布版</option> </select> </devsite-select> <devsite-filter match="all" select-el-container-id="filter-languages"> <input placeholder="依語言或 BCP-47 代碼搜尋" type="text" /> <table> <thead> <tr> <th>語言</th> <th>BCP-47 代碼</th> <th>發布準備完成度</th> </tr> </thead> <tbody class="list"> <tr> <td>阿拉伯文 (埃及)</td> <td>ar-EG</td> <td>正式發布版</td> </tr> <tr> <td>荷蘭文 (荷蘭)</td> <td>nl-NL</td> <td>正式發布版</td> </tr> <tr> <td>英文 (印度)</td> <td>en-IN</td> <td>正式發布版</td> </tr> <tr> <td>英文 (美國)</td> <td>en-US</td> <td>正式發布版</td> </tr> <tr> <td>法文 (法國)</td> <td>fr-FR</td> <td>正式發布版</td> </tr> <tr> <td>德文 (德國)</td> <td>de-DE</td> <td>正式發布版</td> </tr> <tr> <td>北印度文 (印度)</td> <td>hi-IN</td> <td>正式發布版</td> </tr> <tr> <td>印尼文 (印尼)</td> <td>id-ID</td> <td>正式發布版</td> </tr> <tr> <td>義大利文 (義大利)</td> <td>it-IT</td> <td>正式發布版</td> </tr> <tr> <td>日文 (日本)</td> <td>ja-JP</td> <td>正式發布版</td> </tr> <tr> <td>韓文 (韓國)</td> <td>ko-KR</td> <td>正式發布版</td> </tr> <tr> <td>馬拉地文 (印度)</td> <td>mr-IN</td> <td>正式發布版</td> </tr> <tr> <td>波蘭文 (波蘭)</td> <td>pl-PL</td> <td>正式發布版</td> </tr> <tr> <td>葡萄牙文 (巴西)</td> <td>pt-BR</td> <td>正式發布版</td> </tr> <tr> <td>羅馬尼亞文 (羅馬尼亞)</td> <td>ro-RO</td> <td>正式發布版</td> </tr> <tr> <td>俄文 (俄羅斯)</td> <td>ru-RU</td> <td>正式發布版</td> </tr> <tr> <td>西班牙文 (西班牙)</td> <td>es-ES</td> <td>正式發布版</td> </tr> <tr> <td>泰米爾文 (印度)</td> <td>ta-IN</td> <td>正式發布版</td> </tr> <tr> <td>泰盧固文 (印度)</td> <td>te-IN</td> <td>正式發布版</td> </tr> <tr> <td>泰文 (泰國)</td> <td>th-TH</td> <td>正式發布版</td> </tr> <tr> <td>土耳其文 (土耳其)</td> <td>tr-TR</td> <td>正式發布版</td> </tr> <tr> <td>烏克蘭文 (烏克蘭)</td> <td>uk-UA</td> <td>正式發布版</td> </tr> <tr> <td>越南文 (越南)</td> <td>vi-VN</td> <td>正式發布版</td> </tr> <tr> <td>南非荷蘭文 (南非)</td> <td>af-ZA</td> <td>預先發布版</td> </tr> <tr> <td>阿爾巴尼亞文 (阿爾巴尼亞)</td> <td>sq-AL</td> <td>預先發布版</td> </tr> <tr> <td>阿姆哈拉文 (衣索比亞)</td> <td>am-ET</td> <td>預先發布版</td> </tr> <tr> <td>阿拉伯文 (全球)</td> <td>ar-001</td> <td>預先發布版</td> </tr> <tr> <td>亞美尼亞文 (亞美尼亞)</td> <td>hy-AM</td> <td>預先發布版</td> </tr> <tr> <td>亞塞拜然文 (亞塞拜然)</td> <td>az-AZ</td> <td>預先發布版</td> </tr> <tr> <td>孟加拉文 (孟加拉)</td> <td>bn-BD</td> <td>預先發布版</td> </tr> <tr> <td>巴斯克文 (西班牙)</td> <td>eu-ES</td> <td>預先發布版</td> </tr> <tr> <td>白俄羅斯文 (白俄羅斯)</td> <td>be-BY</td> <td>預先發布版</td> </tr> <tr> <td>保加利亞文 (保加利亞)</td> <td>bg-BG</td> <td>預先發布版</td> </tr> <tr> <td>緬甸文 (緬甸)</td> <td>my-MM</td> <td>預先發布版</td> </tr> <tr> <td>加泰隆尼亞文 (西班牙)</td> <td>ca-ES</td> <td>預先發布版</td> </tr> <tr> <td>宿霧文 (菲律賓)</td> <td>ceb-PH</td> <td>預先發布版</td> </tr> <tr> <td>中文/華語 (中國)</td> <td>cmn-CN</td> <td>預先發布版</td> </tr> <tr> <td>中文/華語 (台灣)</td> <td>cmn-tw</td> <td>預先發布版</td> </tr> <tr> <td>克羅埃西亞文 (克羅埃西亞)</td> <td>hr-HR</td> <td>預先發布版</td> </tr> <tr> <td>捷克文 (捷克共和國)</td> <td>cs-CZ</td> <td>預先發布版</td> </tr> <tr> <td>丹麥文 (丹麥)</td> <td>da-DK</td> <td>預先發布版</td> </tr> <tr> <td>英文 (澳洲)</td> <td>en-AU</td> <td>預先發布版</td> </tr> <tr> <td>英文 (英國)</td> <td>en-GB</td> <td>預先發布版</td> </tr> <tr> <td>愛沙尼亞文 (愛沙尼亞)</td> <td>et-EE</td> <td>預先發布版</td> </tr> <tr> <td>菲律賓文 (菲律賓)</td> <td>fil-PH</td> <td>預先發布版</td> </tr> <tr> <td>芬蘭文 (芬蘭)</td> <td>fi-FI</td> <td>預先發布版</td> </tr> <tr> <td>法文 (加拿大)</td> <td>fr-CA</td> <td>預先發布版</td> </tr> <tr> <td>加里西亞文 (西班牙)</td> <td>gl-ES</td> <td>預先發布版</td> </tr> <tr> <td>喬治亞文 (喬治亞)</td> <td>ka-GE</td> <td>預先發布版</td> </tr> <tr> <td>希臘文 (希臘)</td> <td>el-GR</td> <td>預先發布版</td> </tr> <tr> <td>古吉拉特文 (印度)</td> <td>gu-IN</td> <td>預先發布版</td> </tr> <tr> <td>海地克里奧爾文 (海地)</td> <td>ht-HT</td> <td>預先發布版</td> </tr> <tr> <td>希伯來文 (以色列)</td> <td>he-IL</td> <td>預先發布版</td> </tr> <tr> <td>匈牙利文 (匈牙利)</td> <td>hu-HU</td> <td>預先發布版</td> </tr> <tr> <td>冰島文 (冰島)</td> <td>is-IS</td> <td>預先發布版</td> </tr> <tr> <td>爪哇文 (爪哇)</td> <td>jv-JV</td> <td>預先發布版</td> </tr> <tr> <td>卡納達文 (印度)</td> <td>kn-IN</td> <td>預先發布版</td> </tr> <tr> <td>貢根文 (印度)</td> <td>kok-IN</td> <td>預先發布版</td> </tr> <tr> <td>寮文 (寮國)</td> <td>lo-LA</td> <td>預先發布版</td> </tr> <tr> <td>拉丁文 (梵蒂岡)</td> <td>la-VA</td> <td>預先發布版</td> </tr> <tr> <td>拉脫維亞文 (拉脫維亞)</td> <td>lv-LV</td> <td>預先發布版</td> </tr> <tr> <td>立陶宛文 (立陶宛)</td> <td>lt-LT</td> <td>預先發布版</td> </tr> <tr> <td>盧森堡文 (盧森堡)</td> <td>lb-LU</td> <td>預先發布版</td> </tr> <tr> <td>馬其頓文 (北馬其頓)</td> <td>mk-MK</td> <td>預先發布版</td> </tr> <tr> <td>邁蒂利文 (印度)</td> <td>mai-IN</td> <td>預先發布版</td> </tr> <tr> <td>馬達加斯加文 (馬達加斯加)</td> <td>mg-MG</td> <td>預先發布版</td> </tr> <tr> <td>馬來文 (馬來西亞)</td> <td>ms-MY</td> <td>預先發布版</td> </tr> <tr> <td>馬拉雅拉姆文 (印度)</td> <td>ml-IN</td> <td>預先發布版</td> </tr> <tr> <td>蒙古文 (蒙古)</td> <td>mn-MN</td> <td>預先發布版</td> </tr> <tr> <td>尼泊爾文 (尼泊爾)</td> <td>ne-NP</td> <td>預先發布版</td> </tr> <tr> <td>挪威博克馬爾文 (挪威)</td> <td>nb-NO</td> <td>預先發布版</td> </tr> <tr> <td>挪威文/新挪威文 (挪威)</td> <td>nn-NO</td> <td>預先發布版</td> </tr> <tr> <td>歐迪亞文 (印度)</td> <td>or-IN</td> <td>預先發布版</td> </tr> <tr> <td>普什圖文 (阿富汗)</td> <td>ps-AF</td> <td>預先發布版</td> </tr> <tr> <td>波斯文 (伊朗)</td> <td>fa-IR</td> <td>預先發布版</td> </tr> <tr> <td>葡萄牙文 (葡萄牙)</td> <td>pt-PT</td> <td>預先發布版</td> </tr> <tr> <td>旁遮普文 (印度)</td> <td>pa-IN</td> <td>預先發布版</td> </tr> <tr> <td>塞爾維亞文 (塞爾維亞)</td> <td>sr-RS</td> <td>預先發布版</td> </tr> <tr> <td>信德文 (印度)</td> <td>sd-IN</td> <td>預先發布版</td> </tr> <tr> <td>僧伽羅文 (斯里蘭卡)</td> <td>si-LK</td> <td>預先發布版</td> </tr> <tr> <td>斯洛伐克文 (斯洛伐克)</td> <td>sk-SK</td> <td>預先發布版</td> </tr> <tr> <td>斯洛維尼亞文 (斯洛維尼亞)</td> <td>sl-SI</td> <td>預先發布版</td> </tr> <tr> <td>西班牙文 (拉丁美洲)</td> <td>es-419</td> <td>預先發布版</td> </tr> <tr> <td>西班牙文 (墨西哥)</td> <td>es-MX</td> <td>預先發布版</td> </tr> <tr> <td>斯瓦希里文 (肯亞)</td> <td>sw-KE</td> <td>預先發布版</td> </tr> <tr> <td>瑞典文 (瑞典)</td> <td>sv-SE</td> <td>預先發布版</td> </tr> <tr> <td>烏爾都文 (巴基斯坦)</td> <td>ur-PK</td> <td>預先發布版</td> </tr> </tbody> </table> </devsite-filter> </div> <h2 data-text="使用 Gemini-TTS" id="use_gemini-tts" tabindex="-1">使用 Gemini-TTS</h2> <p>瞭解如何使用 Gemini-TTS 模型合成單人和多人語音。</p> <aside class="note"><strong>注意:</strong><span>文字欄位和提示詞欄位的大小上限為 900 個位元組。提示詞和文字欄位的總大小上限為 1,800 個位元組,但每個欄位最多只能有 900 個位元組。</span></aside><aside class="note"><strong>注意:</strong><span>如要使用 Gemini-TTS,模型端點必須具備 <code dir="ltr" translate="no">aiplatform.endpoints.predict</code> 權限。您可以透過 <a href="https://docs.cloud.google.com/vertex-ai/docs/general/access-control?hl=zh-tw#aiplatform.user">roles/aiplatform.user 角色</a>授予這項權限。</span></aside><h3 data-text="事前準備" id="before_you_begin" tabindex="-1">事前準備</h3> <p>您必須先在Google Cloud 控制台啟用 API,才能開始使用 Text-to-Speech,步驟如下:</p> <ol> <li>在專案中啟用 Text-to-Speech</li> <li>確認已啟用 Text-to-Speech 的計費功能。</li> <li>設定開發環境的驗證機制。</li> </ol> <h4 data-text="設定 Google Cloud 專案" id="set_up_your_google_cloud_platform_project" tabindex="-1">設定 Google Cloud 專案</h4> <ol> <li><p><a class="button button-primary" href="https://console.cloud.google.com/?hl=zh-tw" target="console" track-metadata-position="body" track-name="console Link" track-type="tasks">登入 Google Cloud 控制台</a>。</p></li> <li><p><a class="button button-primary" href="https://console.cloud.google.com/projectselector2/home/dashboard?hl=zh-tw"target="console" track-metadata-end-goal="createProject" track-name="consoleLink" track-type="commonIncludes">前往專案選取器頁面</a>。</p> <p>您可以選擇現有專案或建立新專案。如要進一步瞭解如何建立專案,請參閱<a href="https://docs.cloud.google.com/resource-manager/docs/creating-managing-projects?hl=zh-tw" target="_blank">Google Cloud 說明文件</a>。</p></li> <li><p>如果選擇建立新專案,系統會顯示訊息,提示您連結帳單帳戶;如果選擇使用現有專案,請務必啟用計費功能。</p> <p><a class="button button-primary" href="https://docs.cloud.google.com/billing/docs/how-to/modify-project?hl=zh-tw"target="_blank" track-metadata-end-goal="enableBilling" track-name="supportLink" track-type="commonIncludes">瞭解如何確認已啟用專案的計費功能</a></p> <aside class="note"><strong>注意:</strong><span>您必須啟用計費功能,才能使用 Text-to-Speech API,但只有在超出免付費配額時,系統才會向您收費。如要進一步瞭解定價,請參閱<a href="https://cloud.google.com/text-to-speech/pricing?hl=zh-tw">定價</a>頁面。</span></aside></li> <li><p>選取專案並連結到帳單帳戶後,即可啟用 Text-to-Speech API。請前往頁面頂端的「Search products and resources」(搜尋產品和資源) <strong></strong>列,輸入「speech」<strong></strong>,然後從結果清單中選取「Cloud Text-to-Speech API」<strong></strong>。</p></li> <li><p>如要試用 Text-to-Speech,但不想將這項工具連結到專案,請選擇「Try this API」(試用這個 API) <strong></strong>選項。如要啟用 Text-to-Speech API,以便搭配專案使用,請按一下「Enable」(啟用)<strong></strong>。</p></li> <li><p>設定開發環境的驗證機制。如需操作說明,請參閱「<a href="https://docs.cloud.google.com/text-to-speech/docs/authentication?hl=zh-tw#authn-how-to">設定 Text-to-Speech 的驗證機制</a>」。</p></li> </ol> <h3 data-text="執行單一說話者同步合成作業" id="perform_synchronous_single-speaker_synthesis" tabindex="-1">執行單一說話者同步合成作業</h3> <div class="ds-selector-tabs" data-ds-scope="code-sample"> <section><h3 data-text="Python" id="python" tabindex="-1">Python</h3><div></div><devsite-code><pre class="devsite-click-to-copy" translate="no" dir="ltr" is-upgraded syntax="Python"><code translate="no" dir="ltr"><span class="devsite-syntax-c1"># google-cloud-texttospeech minimum version 2.29.0 is required.</span> <span class="devsite-syntax-kn">import</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-nn">os</span> <span class="devsite-syntax-kn">from</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-nn">google.cloud</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-kn">import</span> <span class="devsite-syntax-n">texttospeech</span> <span class="devsite-syntax-n">PROJECT_ID</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">os</span><span class="devsite-syntax-o">.</span><span class="devsite-syntax-n">getenv</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-s2">"GOOGLE_CLOUD_PROJECT"</span><span class="devsite-syntax-p">)</span> <span class="devsite-syntax-k">def</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-nf">synthesize</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-n">prompt</span><span class="devsite-syntax-p">:</span> <span class="devsite-syntax-nb">str</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">text</span><span class="devsite-syntax-p">:</span> <span class="devsite-syntax-nb">str</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">output_filepath</span><span class="devsite-syntax-p">:</span> <span class="devsite-syntax-nb">str</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-s2">"output.mp3"</span><span class="devsite-syntax-p">):</span> <span class="devsite-syntax-w"> </span><span class="devsite-syntax-sd">"""Synthesizes speech from the input text and saves it to an MP3 file.</span> <span class="devsite-syntax-sd"> Args:</span> <span class="devsite-syntax-sd"> prompt: Styling instructions on how to synthesize the content in</span> <span class="devsite-syntax-sd"> the text field.</span> <span class="devsite-syntax-sd"> text: The text to synthesize.</span> <span class="devsite-syntax-sd"> output_filepath: The path to save the generated audio file.</span> <span class="devsite-syntax-sd"> Defaults to "output.mp3".</span> <span class="devsite-syntax-sd"> """</span> <span class="devsite-syntax-n">client</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.services.text_to_speech.TextToSpeechClient.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech.services" track-metadata-xref-link-text="TextToSpeechClient" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">TextToSpeechClient</span></a><span class="devsite-syntax-p">()</span> <span class="devsite-syntax-n">synthesis_input</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.SynthesisInput.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="SynthesisInput" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">SynthesisInput</span></a><span class="devsite-syntax-p">(</span><span class="devsite-syntax-n">text</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">text</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">prompt</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">prompt</span><span class="devsite-syntax-p">)</span> <span class="devsite-syntax-c1"># Select the voice you want to use.</span> <span class="devsite-syntax-n">voice</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.VoiceSelectionParams.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="VoiceSelectionParams" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">VoiceSelectionParams</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">language_code</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"en-US"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">name</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"Charon"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-c1"># Example voice, adjust as needed</span> <span class="devsite-syntax-n">model_name</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"gemini-2.5-pro-tts"</span> <span class="devsite-syntax-p">)</span> <span class="devsite-syntax-n">audio_config</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.AudioConfig.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="AudioConfig" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">AudioConfig</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">audio_encoding</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.AudioEncoding.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="AudioEncoding" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">AudioEncoding</span></a><span class="devsite-syntax-o">.</span><span class="devsite-syntax-n">MP3</span> <span class="devsite-syntax-p">)</span> <span class="devsite-syntax-c1"># Perform the text-to-speech request on the text input with the selected</span> <span class="devsite-syntax-c1"># voice parameters and audio file type.</span> <span class="devsite-syntax-n">response</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">client</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.services.text_to_speech.TextToSpeechClient.html?hl=zh-tw#google_cloud_texttospeech_v1_services_text_to_speech_TextToSpeechClient_synthesize_speech" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech.services" track-metadata-xref-link-text="synthesize_speech" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">synthesize_speech</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-nb">input</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">synthesis_input</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">voice</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">voice</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">audio_config</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">audio_config</span> <span class="devsite-syntax-p">)</span> <span class="devsite-syntax-c1"># The response's audio_content is binary.</span> <span class="devsite-syntax-k">with</span> <span class="devsite-syntax-nb">open</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-n">output_filepath</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-s2">"wb"</span><span class="devsite-syntax-p">)</span> <span class="devsite-syntax-k">as</span> <span class="devsite-syntax-n">out</span><span class="devsite-syntax-p">:</span> <span class="devsite-syntax-n">out</span><span class="devsite-syntax-o">.</span><span class="devsite-syntax-n">write</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-n">response</span><span class="devsite-syntax-o">.</span><span class="devsite-syntax-n">audio_content</span><span class="devsite-syntax-p">)</span> <span class="devsite-syntax-nb">print</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-sa">f</span><span class="devsite-syntax-s2">"Audio content written to file: </span><span class="devsite-syntax-si">{</span><span class="devsite-syntax-n">output_filepath</span><span class="devsite-syntax-si">}</span><span class="devsite-syntax-s2">"</span><span class="devsite-syntax-p">)</span> </code></pre></devsite-code></section> <section><h3 data-text="CURL" id="curl" tabindex="-1">CURL</h3><div></div><devsite-code><pre class="devsite-click-to-copy" translate="no" dir="ltr" is-upgraded syntax="Bash"><code translate="no" dir="ltr"><span class="devsite-syntax-c1"># Make sure to install gcloud cli, and sign in to your project.</span> <span class="devsite-syntax-c1"># Make sure to use your PROJECT_ID value.</span> <span class="devsite-syntax-c1"># The available models are gemini-2.5-flash-tts and gemini-2.5-pro-tts.</span> <span class="devsite-syntax-c1"># To parse the JSON output and use it directly see the last line of the command.</span> <span class="devsite-syntax-c1"># Requires JQ and ffplay library to be installed.</span> <span class="devsite-syntax-nv">PROJECT_ID</span><span class="devsite-syntax-o">=</span><var translate="no">YOUR_PROJECT_ID</var> curl<span class="devsite-syntax-w"> </span>-X<span class="devsite-syntax-w"> </span>POST<span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span>-H<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s2">"Authorization: Bearer </span><span class="devsite-syntax-k">$(</span>gcloud<span class="devsite-syntax-w"> </span>auth<span class="devsite-syntax-w"> </span>application-default<span class="devsite-syntax-w"> </span>print-access-token<span class="devsite-syntax-k">)</span><span class="devsite-syntax-s2">"</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span>-H<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s2">"x-goog-user-project: </span><span class="devsite-syntax-nv">$PROJECT_ID</span><span class="devsite-syntax-s2">"</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span>-H<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s2">"Content-Type: application/json"</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> -d<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s1">'{</span> <span class="devsite-syntax-s1"> "input": {</span> <span class="devsite-syntax-s1"> "prompt": "Say the following in a curious way",</span> <span class="devsite-syntax-s1"> "text": "OK, so... tell me about this [uhm] AI thing."</span> <span class="devsite-syntax-s1"> },</span> <span class="devsite-syntax-s1"> "voice": {</span> <span class="devsite-syntax-s1"> "languageCode": "en-us",</span> <span class="devsite-syntax-s1"> "name": "Kore",</span> <span class="devsite-syntax-s1"> "model_name": "gemini-2.5-flash-tts"</span> <span class="devsite-syntax-s1"> },</span> <span class="devsite-syntax-s1"> "audioConfig": {</span> <span class="devsite-syntax-s1"> "audioEncoding": "LINEAR16"</span> <span class="devsite-syntax-s1"> }</span> <span class="devsite-syntax-s1">}'</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span><span class="devsite-syntax-s2">"https://texttospeech.googleapis.com/v1/text:synthesize"</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span><span class="devsite-syntax-p">|</span><span class="devsite-syntax-w"> </span>jq<span class="devsite-syntax-w"> </span>-r<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s1">'.audioContent'</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-p">|</span><span class="devsite-syntax-w"> </span>base64<span class="devsite-syntax-w"> </span>-d<span class="devsite-syntax-w"> </span><span class="devsite-syntax-p">|</span><span class="devsite-syntax-w"> </span>ffplay<span class="devsite-syntax-w"> </span>-<span class="devsite-syntax-w"> </span>-autoexit </code></pre></devsite-code></section> </div> <h3 data-text="使用任意形式的文字輸入內容,執行多位說話者同步合成作業" id="perform_synchronous_multi-speaker_synthesis_with_freeform_text_input" tabindex="-1">使用任意形式的文字輸入內容,執行多位說話者同步合成作業</h3> <aside class="note"><strong>注意:</strong><span>說話者別名只能包含英數字元,且不得有空白字元。</span></aside><div class="ds-selector-tabs" data-ds-scope="code-sample"> <section><h3 data-text="Python" id="python_1" tabindex="-1">Python</h3><div></div><devsite-code><pre class="devsite-click-to-copy" translate="no" dir="ltr" is-upgraded syntax="Python"><code translate="no" dir="ltr"><span class="devsite-syntax-c1"># google-cloud-texttospeech minimum version 2.31.0 is required.</span> <span class="devsite-syntax-kn">import</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-nn">os</span> <span class="devsite-syntax-kn">from</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-nn">google.cloud</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-kn">import</span> <span class="devsite-syntax-n">texttospeech</span> <span class="devsite-syntax-n">PROJECT_ID</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">os</span><span class="devsite-syntax-o">.</span><span class="devsite-syntax-n">getenv</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-s2">"GOOGLE_CLOUD_PROJECT"</span><span class="devsite-syntax-p">)</span> <span class="devsite-syntax-k">def</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-nf">synthesize_multispeaker_freeform</span><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">prompt</span><span class="devsite-syntax-p">:</span> <span class="devsite-syntax-nb">str</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">text</span><span class="devsite-syntax-p">:</span> <span class="devsite-syntax-nb">str</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">output_filepath</span><span class="devsite-syntax-p">:</span> <span class="devsite-syntax-nb">str</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-s2">"output_non_turn_based.wav"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-p">):</span> <span class="devsite-syntax-w"> </span><span class="devsite-syntax-sd">"""Synthesizes speech from non-turn-based input and saves it to a WAV file.</span> <span class="devsite-syntax-sd"> Args:</span> <span class="devsite-syntax-sd"> prompt: Styling instructions on how to synthesize the content in the</span> <span class="devsite-syntax-sd"> text field.</span> <span class="devsite-syntax-sd"> text: The text to synthesize, containing speaker aliases to indicate</span> <span class="devsite-syntax-sd"> different speakers. Example: "Sam: Hi Bob!\nBob: Hi Sam!"</span> <span class="devsite-syntax-sd"> output_filepath: The path to save the generated audio file. Defaults to</span> <span class="devsite-syntax-sd"> "output_non_turn_based.wav".</span> <span class="devsite-syntax-sd"> """</span> <span class="devsite-syntax-n">client</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.services.text_to_speech.TextToSpeechClient.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech.services" track-metadata-xref-link-text="TextToSpeechClient" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">TextToSpeechClient</span></a><span class="devsite-syntax-p">()</span> <span class="devsite-syntax-n">synthesis_input</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.SynthesisInput.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="SynthesisInput" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">SynthesisInput</span></a><span class="devsite-syntax-p">(</span><span class="devsite-syntax-n">text</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">text</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">prompt</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">prompt</span><span class="devsite-syntax-p">)</span> <span class="devsite-syntax-n">multi_speaker_voice_config</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.MultiSpeakerVoiceConfig.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="MultiSpeakerVoiceConfig" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">MultiSpeakerVoiceConfig</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">speaker_voice_configs</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-p">[</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.MultispeakerPrebuiltVoice.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="MultispeakerPrebuiltVoice" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">MultispeakerPrebuiltVoice</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">speaker_alias</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"Speaker1"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">speaker_id</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"Kore"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-p">),</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.MultispeakerPrebuiltVoice.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="MultispeakerPrebuiltVoice" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">MultispeakerPrebuiltVoice</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">speaker_alias</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"Speaker2"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">speaker_id</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"Charon"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-p">),</span> <span class="devsite-syntax-p">]</span> <span class="devsite-syntax-p">)</span> <span class="devsite-syntax-n">voice</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.VoiceSelectionParams.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="VoiceSelectionParams" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">VoiceSelectionParams</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">language_code</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"en-US"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">model_name</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"gemini-2.5-pro-tts"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">multi_speaker_voice_config</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">multi_speaker_voice_config</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-p">)</span> <span class="devsite-syntax-n">audio_config</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.AudioConfig.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="AudioConfig" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">AudioConfig</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">audio_encoding</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.AudioEncoding.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="AudioEncoding" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">AudioEncoding</span></a><span class="devsite-syntax-o">.</span><span class="devsite-syntax-n">LINEAR16</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">sample_rate_hertz</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-mi">24000</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-p">)</span> <span class="devsite-syntax-n">response</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">client</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.services.text_to_speech.TextToSpeechClient.html?hl=zh-tw#google_cloud_texttospeech_v1_services_text_to_speech_TextToSpeechClient_synthesize_speech" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech.services" track-metadata-xref-link-text="synthesize_speech" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">synthesize_speech</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-nb">input</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">synthesis_input</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">voice</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">voice</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">audio_config</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">audio_config</span> <span class="devsite-syntax-p">)</span> <span class="devsite-syntax-k">with</span> <span class="devsite-syntax-nb">open</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-n">output_filepath</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-s2">"wb"</span><span class="devsite-syntax-p">)</span> <span class="devsite-syntax-k">as</span> <span class="devsite-syntax-n">out</span><span class="devsite-syntax-p">:</span> <span class="devsite-syntax-n">out</span><span class="devsite-syntax-o">.</span><span class="devsite-syntax-n">write</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-n">response</span><span class="devsite-syntax-o">.</span><span class="devsite-syntax-n">audio_content</span><span class="devsite-syntax-p">)</span> <span class="devsite-syntax-nb">print</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-sa">f</span><span class="devsite-syntax-s2">"Audio content written to file: </span><span class="devsite-syntax-si">{</span><span class="devsite-syntax-n">output_filepath</span><span class="devsite-syntax-si">}</span><span class="devsite-syntax-s2">"</span><span class="devsite-syntax-p">)</span> </code></pre></devsite-code></section> <section><h3 data-text="CURL" id="curl_1" tabindex="-1">CURL</h3><div></div><devsite-code><pre class="devsite-click-to-copy" translate="no" dir="ltr" is-upgraded syntax="Bash"><code translate="no" dir="ltr"><span class="devsite-syntax-c1"># Make sure to install gcloud cli, and sign in to your project.</span> <span class="devsite-syntax-c1"># Make sure to use your PROJECT_ID value.</span> <span class="devsite-syntax-c1"># The available models are gemini-2.5-flash-tts and gemini-2.5-pro-tts</span> <span class="devsite-syntax-c1"># To parse the JSON output and use it directly see the last line of the command.</span> <span class="devsite-syntax-c1"># Requires JQ and ffplay library to be installed.</span> <span class="devsite-syntax-c1"># google-cloud-texttospeech minimum version 2.31.0 is required.</span> <span class="devsite-syntax-nv">PROJECT_ID</span><span class="devsite-syntax-o">=</span><var translate="no">YOUR_PROJECT_ID</var> curl<span class="devsite-syntax-w"> </span>-X<span class="devsite-syntax-w"> </span>POST<span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span>-H<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s2">"Authorization: Bearer </span><span class="devsite-syntax-k">$(</span>gcloud<span class="devsite-syntax-w"> </span>auth<span class="devsite-syntax-w"> </span>application-default<span class="devsite-syntax-w"> </span>print-access-token<span class="devsite-syntax-k">)</span><span class="devsite-syntax-s2">"</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span>-H<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s2">"x-goog-user-project: </span><span class="devsite-syntax-nv">$PROJECT_ID</span><span class="devsite-syntax-s2">"</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span>-H<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s2">"Content-Type: application/json"</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> -d<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s1">'{</span> <span class="devsite-syntax-s1"> "input": {</span> <span class="devsite-syntax-s1"> "prompt": "Say the following as a conversation between friends.",</span> <span class="devsite-syntax-s1"> "text": "Sam: Hi Bob, how are you?\\nBob: I am doing well, and you?"</span> <span class="devsite-syntax-s1"> },</span> <span class="devsite-syntax-s1"> "voice": {</span> <span class="devsite-syntax-s1"> "languageCode": "en-us",</span> <span class="devsite-syntax-s1"> "modelName": "gemini-2.5-flash-tts",</span> <span class="devsite-syntax-s1"> "multiSpeakerVoiceConfig": {</span> <span class="devsite-syntax-s1"> "speakerVoiceConfigs": [</span> <span class="devsite-syntax-s1"> {</span> <span class="devsite-syntax-s1"> "speakerAlias": "Sam",</span> <span class="devsite-syntax-s1"> "speakerId": "Kore"</span> <span class="devsite-syntax-s1"> },</span> <span class="devsite-syntax-s1"> {</span> <span class="devsite-syntax-s1"> "speakerAlias": "Bob",</span> <span class="devsite-syntax-s1"> "speakerId": "Charon"</span> <span class="devsite-syntax-s1"> }</span> <span class="devsite-syntax-s1"> ]</span> <span class="devsite-syntax-s1"> }</span> <span class="devsite-syntax-s1"> },</span> <span class="devsite-syntax-s1"> "audioConfig": {</span> <span class="devsite-syntax-s1"> "audioEncoding": "LINEAR16",</span> <span class="devsite-syntax-s1"> "sampleRateHertz": 24000</span> <span class="devsite-syntax-s1"> }</span> <span class="devsite-syntax-s1">}'</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span><span class="devsite-syntax-s2">"https://texttospeech.googleapis.com/v1/text:synthesize"</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span><span class="devsite-syntax-p">|</span><span class="devsite-syntax-w"> </span>jq<span class="devsite-syntax-w"> </span>-r<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s1">'.audioContent'</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-p">|</span><span class="devsite-syntax-w"> </span>base64<span class="devsite-syntax-w"> </span>-d<span class="devsite-syntax-w"> </span><span class="devsite-syntax-p">|</span><span class="devsite-syntax-w"> </span>ffplay<span class="devsite-syntax-w"> </span>-<span class="devsite-syntax-w"> </span>-autoexit </code></pre></devsite-code></section> </div> <h3 data-text="使用結構化文字輸入內容,執行多位說話者同步合成作業" id="perform_synchronous_multi-speaker_synthesis_with_structured_text_input" tabindex="-1">使用結構化文字輸入內容,執行多位說話者同步合成作業</h3> <p>根據結構化文字輸入內容,以類似人類的口吻將文字轉換成多人語音。舉例來說,這類輸入內容適用於地址和日期。如果是任意形式的文字輸入內容,系統會完全按照撰寫內容朗讀。</p> <aside class="note"><strong>注意:</strong><span>所有對話行的總大小上限為 900 個位元組。提示詞和對話的總大小上限為 1,800 個位元組,但每個提示詞和對話欄位最多只能有 900 個位元組。說話者別名只能包含英數字元,且不得有空白字元。</span></aside><div class="ds-selector-tabs" data-ds-scope="code-sample"> <section><h3 data-text="Python" id="python_2" tabindex="-1">Python</h3><div></div><devsite-code><pre class="devsite-click-to-copy" translate="no" dir="ltr" is-upgraded syntax="Python"><code translate="no" dir="ltr"><span class="devsite-syntax-c1"># google-cloud-texttospeech minimum version 2.31.0 is required.</span> <span class="devsite-syntax-kn">import</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-nn">os</span> <span class="devsite-syntax-kn">from</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-nn">google.cloud</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-kn">import</span> <span class="devsite-syntax-n">texttospeech</span> <span class="devsite-syntax-n">PROJECT_ID</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">os</span><span class="devsite-syntax-o">.</span><span class="devsite-syntax-n">getenv</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-s2">"GOOGLE_CLOUD_PROJECT"</span><span class="devsite-syntax-p">)</span> <span class="devsite-syntax-k">def</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-nf">synthesize_multispeaker_structured</span><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">prompt</span><span class="devsite-syntax-p">:</span> <span class="devsite-syntax-nb">str</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">turns</span><span class="devsite-syntax-p">:</span> <span class="devsite-syntax-nb">list</span><span class="devsite-syntax-p">[</span><span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.MultiSpeakerMarkup.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="MultiSpeakerMarkup" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">MultiSpeakerMarkup</span></a><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.MultiSpeakerMarkup.Turn.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="Turn" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">Turn</span></a><span class="devsite-syntax-p">],</span> <span class="devsite-syntax-n">output_filepath</span><span class="devsite-syntax-p">:</span> <span class="devsite-syntax-nb">str</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-s2">"output_turn_based.wav"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-p">):</span> <span class="devsite-syntax-w"> </span><span class="devsite-syntax-sd">"""Synthesizes speech from turn-based input and saves it to a WAV file.</span> <span class="devsite-syntax-sd"> Args:</span> <span class="devsite-syntax-sd"> prompt: Styling instructions on how to synthesize the content in the</span> <span class="devsite-syntax-sd"> text field.</span> <span class="devsite-syntax-sd"> turns: A list of texttospeech.MultiSpeakerMarkup.Turn objects representing</span> <span class="devsite-syntax-sd"> the dialogue turns.</span> <span class="devsite-syntax-sd"> output_filepath: The path to save the generated audio file. Defaults to</span> <span class="devsite-syntax-sd"> "output_turn_based.wav".</span> <span class="devsite-syntax-sd"> """</span> <span class="devsite-syntax-n">client</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.services.text_to_speech.TextToSpeechClient.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech.services" track-metadata-xref-link-text="TextToSpeechClient" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">TextToSpeechClient</span></a><span class="devsite-syntax-p">()</span> <span class="devsite-syntax-n">synthesis_input</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.SynthesisInput.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="SynthesisInput" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">SynthesisInput</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">multi_speaker_markup</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.MultiSpeakerMarkup.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="MultiSpeakerMarkup" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">MultiSpeakerMarkup</span></a><span class="devsite-syntax-p">(</span><span class="devsite-syntax-n">turns</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">turns</span><span class="devsite-syntax-p">),</span> <span class="devsite-syntax-n">prompt</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">prompt</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-p">)</span> <span class="devsite-syntax-n">multi_speaker_voice_config</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.MultiSpeakerVoiceConfig.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="MultiSpeakerVoiceConfig" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">MultiSpeakerVoiceConfig</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">speaker_voice_configs</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-p">[</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.MultispeakerPrebuiltVoice.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="MultispeakerPrebuiltVoice" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">MultispeakerPrebuiltVoice</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">speaker_alias</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"Speaker1"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">speaker_id</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"Kore"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-p">),</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.MultispeakerPrebuiltVoice.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="MultispeakerPrebuiltVoice" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">MultispeakerPrebuiltVoice</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">speaker_alias</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"Speaker2"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">speaker_id</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"Charon"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-p">),</span> <span class="devsite-syntax-p">]</span> <span class="devsite-syntax-p">)</span> <span class="devsite-syntax-n">voice</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.VoiceSelectionParams.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="VoiceSelectionParams" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">VoiceSelectionParams</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">language_code</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"en-US"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">model_name</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-s2">"gemini-2.5-pro-tts"</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">multi_speaker_voice_config</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">multi_speaker_voice_config</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-p">)</span> <span class="devsite-syntax-n">audio_config</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.AudioConfig.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="AudioConfig" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">AudioConfig</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-n">audio_encoding</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">texttospeech</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.types.AudioEncoding.html?hl=zh-tw" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech" track-metadata-xref-link-text="AudioEncoding" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">AudioEncoding</span></a><span class="devsite-syntax-o">.</span><span class="devsite-syntax-n">LINEAR16</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">sample_rate_hertz</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-mi">24000</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-p">)</span> <span class="devsite-syntax-n">response</span> <span class="devsite-syntax-o">=</span> <span class="devsite-syntax-n">client</span><span class="devsite-syntax-o">.</span><a class="devsite-xref-link" href="https://cloud.google.com/python/docs/reference/texttospeech/latest/google.cloud.texttospeech_v1.services.text_to_speech.TextToSpeechClient.html?hl=zh-tw#google_cloud_texttospeech_v1_services_text_to_speech_TextToSpeechClient_synthesize_speech" track-metadata-xref-lang="PYTHON" track-metadata-xref-library="google.cloud.texttospeech.services" track-metadata-xref-link-text="synthesize_speech" track-name="xrefLink" track-type="exampleCode"><span class="devsite-syntax-n">synthesize_speech</span></a><span class="devsite-syntax-p">(</span> <span class="devsite-syntax-nb">input</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">synthesis_input</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">voice</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">voice</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-n">audio_config</span><span class="devsite-syntax-o">=</span><span class="devsite-syntax-n">audio_config</span> <span class="devsite-syntax-p">)</span> <span class="devsite-syntax-k">with</span> <span class="devsite-syntax-nb">open</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-n">output_filepath</span><span class="devsite-syntax-p">,</span> <span class="devsite-syntax-s2">"wb"</span><span class="devsite-syntax-p">)</span> <span class="devsite-syntax-k">as</span> <span class="devsite-syntax-n">out</span><span class="devsite-syntax-p">:</span> <span class="devsite-syntax-n">out</span><span class="devsite-syntax-o">.</span><span class="devsite-syntax-n">write</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-n">response</span><span class="devsite-syntax-o">.</span><span class="devsite-syntax-n">audio_content</span><span class="devsite-syntax-p">)</span> <span class="devsite-syntax-nb">print</span><span class="devsite-syntax-p">(</span><span class="devsite-syntax-sa">f</span><span class="devsite-syntax-s2">"Audio content written to file: </span><span class="devsite-syntax-si">{</span><span class="devsite-syntax-n">output_filepath</span><span class="devsite-syntax-si">}</span><span class="devsite-syntax-s2">"</span><span class="devsite-syntax-p">)</span> </code></pre></devsite-code></section> <section><h3 data-text="CURL" id="curl_2" tabindex="-1">CURL</h3><div></div><devsite-code><pre class="devsite-click-to-copy" translate="no" dir="ltr" is-upgraded syntax="Bash"><code translate="no" dir="ltr"><span class="devsite-syntax-c1"># Make sure to install gcloud cli, and sign in to your project.</span> <span class="devsite-syntax-c1"># Make sure to use your PROJECT_ID value.</span> <span class="devsite-syntax-c1"># The available models are gemini-2.5-flash-tts and gemini-2.5-pro-tts.</span> <span class="devsite-syntax-c1"># To parse the JSON output and use it directly see the last line of the command.</span> <span class="devsite-syntax-c1"># Requires JQ and ffplay library to be installed.</span> <span class="devsite-syntax-c1"># google-cloud-texttospeech minimum version 2.31.0 is required.</span> <span class="devsite-syntax-nv">PROJECT_ID</span><span class="devsite-syntax-o">=</span><var translate="no">YOUR_PROJECT_ID</var> curl<span class="devsite-syntax-w"> </span>-X<span class="devsite-syntax-w"> </span>POST<span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span>-H<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s2">"Authorization: Bearer </span><span class="devsite-syntax-k">$(</span>gcloud<span class="devsite-syntax-w"> </span>auth<span class="devsite-syntax-w"> </span>application-default<span class="devsite-syntax-w"> </span>print-access-token<span class="devsite-syntax-k">)</span><span class="devsite-syntax-s2">"</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span>-H<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s2">"x-goog-user-project: </span><span class="devsite-syntax-nv">$PROJECT_ID</span><span class="devsite-syntax-s2">"</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span>-H<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s2">"Content-Type: application/json"</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> -d<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s1">'{</span> <span class="devsite-syntax-s1"> "input": {</span> <span class="devsite-syntax-s1"> "prompt": "Say the following as a conversation between friends.",</span> <span class="devsite-syntax-s1"> "multiSpeakerMarkup": {</span> <span class="devsite-syntax-s1"> "turns": [</span> <span class="devsite-syntax-s1"> {</span> <span class="devsite-syntax-s1"> "speaker": "Sam",</span> <span class="devsite-syntax-s1"> "text": "Hi Bob, how are you?"</span> <span class="devsite-syntax-s1"> },</span> <span class="devsite-syntax-s1"> {</span> <span class="devsite-syntax-s1"> "speaker": "Bob",</span> <span class="devsite-syntax-s1"> "text": "I am doing well, and you?"</span> <span class="devsite-syntax-s1"> }</span> <span class="devsite-syntax-s1"> ]</span> <span class="devsite-syntax-s1"> }</span> <span class="devsite-syntax-s1"> },</span> <span class="devsite-syntax-s1"> "voice": {</span> <span class="devsite-syntax-s1"> "languageCode": "en-us",</span> <span class="devsite-syntax-s1"> "modelName": "gemini-2.5-flash-tts",</span> <span class="devsite-syntax-s1"> "multiSpeakerVoiceConfig": {</span> <span class="devsite-syntax-s1"> "speakerVoiceConfigs": [</span> <span class="devsite-syntax-s1"> {</span> <span class="devsite-syntax-s1"> "speakerAlias": "Sam",</span> <span class="devsite-syntax-s1"> "speakerId": "Kore"</span> <span class="devsite-syntax-s1"> },</span> <span class="devsite-syntax-s1"> {</span> <span class="devsite-syntax-s1"> "speakerAlias": "Bob",</span> <span class="devsite-syntax-s1"> "speakerId": "Charon"</span> <span class="devsite-syntax-s1"> }</span> <span class="devsite-syntax-s1"> ]</span> <span class="devsite-syntax-s1"> }</span> <span class="devsite-syntax-s1"> },</span> <span class="devsite-syntax-s1"> "audioConfig": {</span> <span class="devsite-syntax-s1"> "audioEncoding": "LINEAR16",</span> <span class="devsite-syntax-s1"> "sampleRateHertz": 24000</span> <span class="devsite-syntax-s1"> }</span> <span class="devsite-syntax-s1">}'</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span><span class="devsite-syntax-s2">"https://texttospeech.googleapis.com/v1/text:synthesize"</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-se">\</span> <span class="devsite-syntax-w"> </span><span class="devsite-syntax-p">|</span><span class="devsite-syntax-w"> </span>jq<span class="devsite-syntax-w"> </span>-r<span class="devsite-syntax-w"> </span><span class="devsite-syntax-s1">'.audioContent'</span><span class="devsite-syntax-w"> </span><span class="devsite-syntax-p">|</span><span class="devsite-syntax-w"> </span>base64<span class="devsite-syntax-w"> </span>-d<span class="devsite-syntax-w"> </span><span class="devsite-syntax-p">|</span><span class="devsite-syntax-w"> </span>ffplay<span class="devsite-syntax-w"> </span>-<span class="devsite-syntax-w"> </span>-autoexit </code></pre></devsite-code></section> </div> <h2 data-text="在 Media Studio 中執行語音合成作業" id="perform_speech_synthesis_in_media_studio" tabindex="-1">在 Media Studio 中執行語音合成作業</h2> <p>您可以在 Google Google Cloud 控制台透過 Media Studio 試用文字轉語音模型。這個使用者介面可快速生成及聆聽合成音訊,並測試不同的風格指令和參數。</p> <ol> <li><p>在 Google Google Cloud 控制台中,依序前往「Vertex AI Studio」<span aria-label="接下來">></span>「Media Studio」<strong></strong>頁面。</p> <p><a class="button button-primary" href="https://console.cloud.google.com/vertex-ai/studio/media/generate;tab=audio?hl=zh-tw"target="console" track-metadata-position="body" track-name="consoleLink" track-type="task"> Media Studio</a></p></li> <li><p>從媒體下拉式選單中選取「Speech」(語音)<strong></strong>。</p></li> <li><p>在文字欄位中,輸入要合成語音的文字。</p></li> <li><p>在「Settings」(設定)<strong></strong> 窗格中完成下列設定:</p> <ol> <li><strong>模型</strong>:選取要使用的文字轉語音 (TTS) 模型,例如 <code dir="ltr" translate="no">Gemini 2.5 Pro TTS</code>。如要進一步瞭解可用模型,請參閱「<a href="https://docs.cloud.google.com/list-voices-and-types?hl=zh-tw">文字轉語音模型</a>」。</li> <li><strong>風格指令</strong>:(選用) 輸入文字提示詞,描述想要的說話風格、語氣和情緒,藉此引導模型,讓最終的語音表現超越預設水準。例如:「Narrate in a calm, professional tone for a documentary.」(以平靜專業的語氣為紀錄片配旁白。)<em></em></li> <li><strong>語言</strong>:選取輸入文字的語言和地區。模型會以所選語言和口音生成語音,例如「English (United States)」(英文 (美國))<em></em>。</li> <li><strong>語音</strong>:選擇預先定義的旁白語音。清單會顯示所選模型和語言的可用語音,例如「Acherner (Female)」(Acherner (女性))<em></em>。</li> </ol></li> <li><p>(選用) 展開「Advanced options」(進階選項) 部分,設定音訊技術設定:</p> <ol> <li><strong>音訊編碼</strong>:選取輸出音訊檔案的編碼方式。<code dir="ltr" translate="no">LINEAR16</code> 是無失真且未經壓縮的格式,適合用於處理高品質音訊。<code dir="ltr" translate="no">MULAW</code> 也適用於輸出壓縮音訊。</li> <li><strong>音訊取樣率</strong>:選擇取樣率,單位為赫茲 (Hz)。這項設定會決定音質。這個值越高 (例如 44,100 Hz),代表音訊保真度越高,相當於 CD 音質。</li> <li><strong>速度</strong>:移動滑桿或輸入值,即可調整語速。值低於 1.0 會減緩語速,值高於 1.0 則會加快語速,預設值為 1。</li> <li><strong>音量增益 (分貝)</strong>:以分貝 (dB) 為單位調整輸出音訊的音量。正值會調高音量,負值則會調低音量。預設值為 0。</li> </ol></li> <li><p>按一下文字方塊右側的「傳送」<strong></strong>圖示,即可生成音訊。</p></li> <li><p>生成的音訊會顯示在媒體播放器中,點按播放按鈕即可聆聽輸出內容。您可以繼續調整設定,並視需要生成新版本。</p></li> </ol> <h2 data-text="提示詞訣竅" id="prompting_tips" tabindex="-1">提示詞訣竅</h2> <p>如要根據文字內容建立自然流暢的語音,必須先瞭解口語表達與將口語轉換成腳本的細微差異。請參考下列訣竅,撰寫出真實且符合所選語氣的腳本。</p> <h3 data-text="語音控制的三個技巧" id="the_three_levers_of_speech_control" tabindex="-1">語音控制的三個技巧</h3> <p>如要獲得可預測性最高且細緻的結果,請確保下列三個元件都與所需輸出內容一致。</p> <p><strong>風格提示詞</strong>:主要用來決定整體情緒基調和傳達方式,這個提示詞會為整段語音設定情境。</p> <ul> <li><p>範例:<code dir="ltr" translate="no">You are an AI assistant speaking in a friendly and helpful tone.</code></p></li> <li><p>範例:<code dir="ltr" translate="no">Narrate this in the calm, authoritative tone of a nature documentary narrator.</code></p></li> </ul> <p><strong>文字內容</strong>:您要合成的字詞語意。如果使用的詞組與風格提示詞的情緒一致,會比使用中性文字產生出更可靠的結果。</p> <ul> <li><p>效果良好:如果要用提示詞指示系統生成驚恐語氣,最適合搭配「<code dir="ltr" translate="no">I think someone is in the house.</code>」這類文字</p></li> <li><p>效果較差:如果要用提示詞指示系統生成驚恐語氣,但文字內容是「<code dir="ltr" translate="no">The meeting is at 4 PM.</code>」,就會產生模稜兩可的結果</p></li> </ul> <p><strong>標記</strong>:方括號標記 (例如 <code dir="ltr" translate="no">[sigh]</code>) 最適合用於插入特定本地化動作或風格修改項目,而非設定整體語氣。這些標記可與風格提示詞和文字內容相互配合。</p> <h3 data-text="標記指南" id="markup_tag_guide" tabindex="-1">標記指南</h3> <p>研究顯示,用方括號括住的標記會以三種不同模式運作。瞭解標記模式是有效使用標記的關鍵。</p> <h4 data-text="模式 1:非語音聲音" id="mode_1_non-speech_sounds" tabindex="-1">模式 1:非語音聲音</h4> <p>標記會替換為可聽見的非語音發聲 (例如嘆氣、笑聲)。系統不會唸出標記本身。這類語音很適合加入真實、類似人類的遲疑和反應。</p> <table> <thead> <tr> <th style="text-align: left">標記</th> <th style="text-align: left">行為</th> <th style="text-align: left">可靠性</th> <th style="text-align: left">指引</th> </tr> </thead> <tbody> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[sigh]</code></td> <td style="text-align: left">插入嘆氣聲。</td> <td style="text-align: left">高</td> <td style="text-align: left">嘆氣的情緒品質會受到提示詞影響。</td> </tr> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[laughing]</code></td> <td style="text-align: left">插入笑聲。</td> <td style="text-align: left">高</td> <td style="text-align: left">為達最佳效果,請使用具體提示詞。比方說,一般提示詞可能會產生驚訝的笑聲,而「react with an amused laugh」(用開心的笑聲回應) 則會產生愉悅的笑聲。</td> </tr> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[uhm]</code></td> <td style="text-align: left">插入猶豫聲。</td> <td style="text-align: left">高</td> <td style="text-align: left">有助於營造更自然流暢的對話感。</td> </tr> </tbody> </table> <h4 data-text="模式 2:風格修飾符" id="mode_2_style_modifiers" tabindex="-1">模式 2:風格修飾符</h4> <p>系統不會朗讀標記,但會調整後續語音的傳達方式。調整的範圍和時間長度可能有所不同。</p> <table> <thead> <tr> <th style="text-align: left">標記</th> <th style="text-align: left">行為</th> <th style="text-align: left">可靠性</th> <th style="text-align: left">指引</th> </tr> </thead> <tbody> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[sarcasm]</code></td> <td style="text-align: left">為後續詞組加上諷刺的語氣。</td> <td style="text-align: left">高</td> <td style="text-align: left">這個標記是強大的修飾符,表示抽象概念可以成功引導模型的傳達語氣。</td> </tr> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[robotic]</code></td> <td style="text-align: left">使後續語音聽起來像機器人。</td> <td style="text-align: left">高</td> <td style="text-align: left">效果可套用到整個詞組。我們仍建議使用支持性風格提示詞 (例如「Say this in a robotic way」(用機器人語氣說這段文字)),以利獲得最佳結果。</td> </tr> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[shouting]</code></td> <td style="text-align: left">調高後續語音的音量。</td> <td style="text-align: left">高</td> <td style="text-align: left">搭配相符的風格提示詞 (例如「Shout this next part」(大聲說出下一段內容)) 和暗示大聲說話的文字,效果最佳。</td> </tr> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[whispering]</code></td> <td style="text-align: left">降低後續語音的音量。</td> <td style="text-align: left">高</td> <td style="text-align: left">如果風格提示詞也很明確 (例如「now whisper this part as quietly as you can」(現在盡可能輕聲細語地說出這段文字)),可獲得最佳結果。</td> </tr> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[extremely fast]</code></td> <td style="text-align: left">提高後續語音的速度。</td> <td style="text-align: left">高</td> <td style="text-align: left">適合用於免責事項或快速對話,幾乎不用進行提示工程。</td> </tr> </tbody> </table> <h4 data-text="模式 3:發音標記 (形容詞)" id="mode_3_vocalized_markup_adjectives" tabindex="-1">模式 3:發音標記 (形容詞)</h4> <p>標記本身會以單字形式朗讀,同時影響整個句子的語氣。這種行為通常適用於情緒形容詞。</p> <p>警告<em></em>:系統會朗讀標記本身,因此在大多數情況下,這個模式可能會產生不必要的連帶效應。建議改用風格提示詞來設定情緒基調。</p> <table> <thead> <tr> <th style="text-align: left">標記</th> <th style="text-align: left">行為</th> <th style="text-align: left">可靠性</th> <th style="text-align: left">指引</th> </tr> </thead> <tbody> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[scared]</code></td> <td style="text-align: left">說出「scared」(害怕) 一詞,句子會採用害怕的語氣。</td> <td style="text-align: left">高</td> <td style="text-align: left">語氣效果取決於文字內容。「I just heard a window break」(我剛才聽到窗戶破裂聲) 這句話會產生確切害怕的結果。中性詞組會產生「詭異」但較不真實的結果。</td> </tr> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[curious]</code></td> <td style="text-align: left">說出「curious」(好奇) 一詞,句子會採用好奇的語氣。</td> <td style="text-align: left">高</td> <td style="text-align: left">使用疑問句支援標記的意圖。</td> </tr> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[bored]</code></td> <td style="text-align: left">說出「bored」(無聊) 一詞,句子會採用無聊的平淡語氣。</td> <td style="text-align: left">高</td> <td style="text-align: left">建議搭配平淡或重複的文字使用,效果最佳。</td> </tr> </tbody> </table> <h4 data-text="模式 4:節奏和停頓" id="mode_4_pacing_and_pauses" tabindex="-1">模式 4:節奏和停頓</h4> <p>這些標記會在生成的音訊中插入停頓,讓您精細控制節奏、時間和速度。標準標點符號 (逗號、句號、分號) 也會產生自然停頓,但使用這些標記可更明確的控管效果。</p> <table> <thead> <tr> <th style="text-align: left">標記</th> <th style="text-align: left">行為</th> <th style="text-align: left">可靠性</th> <th style="text-align: left">指引</th> </tr> </thead> <tbody> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[short pause]</code></td> <td style="text-align: left">插入短暫停頓,類似於逗號 (~250 毫秒)。</td> <td style="text-align: left">高</td> <td style="text-align: left">用來分隔子句或清單項目,讓內容更清楚。</td> </tr> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[medium pause]</code></td> <td style="text-align: left">插入標準停頓,類似於句子中斷 (約 500 毫秒)。</td> <td style="text-align: left">高</td> <td style="text-align: left">有效分隔不同句子或想法。</td> </tr> <tr> <td style="text-align: left"><code dir="ltr" translate="no">[long pause]</code></td> <td style="text-align: left">插入明顯的停頓,營造戲劇性效果 (約 1000 毫秒以上)。</td> <td style="text-align: left">高</td> <td style="text-align: left">用於營造戲劇性效果,例如:「The answer is...<code dir="ltr" translate="no">[long pause]</code>...no.」(答案是…拒絕。)請避免過度使用,否則聽起來會不自然。</td> </tr> </tbody> </table> <h4 data-text="確保結果可靠的關鍵策略" id="key_strategies_for_reliable_results" tabindex="-1">確保結果可靠的關鍵策略</h4> <ul> <li><p>善用所有三個技巧。為獲得可預測性最高的結果,請確認風格提示詞、文字內容和所有標記在語意方面都保持一致,而且鎖定相同目標。</p></li> <li><p>使用情感豐富的文字。不要只依賴提示詞和標記。提供豐富的描述性文字,讓模型據此生成內容。如果想呈現諷刺、恐懼或興奮等細微情緒,這點尤其重要。</p></li> <li><p>輸入具體詳細的提示詞。風格提示詞越具體,結果就越可靠。比方說,「React with an amused laugh」(用開心的笑聲回應) 比單純的 <code dir="ltr" translate="no">[laughing]</code> 更能傳達情緒。「Speak like a 1940s radio news announcer」(用 1940 年代的電台新聞播報員風格說話) 比「Speak in an old-fashioned way」(用老派風格說話) 更能獲得最佳效果。</p></li> <li><p>測試及驗證新標記。如果是新標記或未經測試的標記,行為有時會難以預測。您認為是風格修飾符的標記可能會發音。因此,請務必先測試新的標記或提示詞組合,確認行為後,再部署到正式環境。</p></li> </ul> <devsite-hats-survey class="nocontent" data-nosnippet hats-id="Nd7nTix2o0eU5NUYprb0ThtUc5jf" listnr-id="83405"></devsite-hats-survey> </div> <devsite-thumb-rating position="footer"> </devsite-thumb-rating> <devsite-feedback position="footer" project-name="Cloud Text-to-Speech" product-id="5041938" bucket="Documentation" context="Cloud Text-to-Speech API docs feedback link" version="t-devsite-webserver-20260825-r00-rc00.479916215390653058" data-label="Send Feedback Button" track-type="feedback" track-name="sendFeedbackLink" track-metadata-position="footer" class="nocontent" data-nosnippet project-feedback-url="https://issuetracker.google.com/issues/new?component=451645" project-icon="https://docs.cloud.google.com/_static/clouddocs/images/icons/categories/ai-and-machine-learning-color.svg?hl=zh-tw" project-support-url="https://docs.cloud.google.com/text-to-speech/docs/support?hl=zh-tw" > <button> 提供意見 </button> </devsite-feedback> <div class="devsite-floating-action-buttons"></div></article> <devsite-content-footer class="nocontent" data-nosnippet> <p>除非另有註明,否則本頁面中的內容是採用<a href="https://creativecommons.org/licenses/by/4.0/">創用 CC 姓名標示 4.0 授權</a>,程式碼範例則為<a href="https://www.apache.org/licenses/LICENSE-2.0">阿帕契 2.0 授權</a>。詳情請參閱《<a href="https://developers.google.com/site-policies?hl=zh-tw">Google Developers 網站政策</a>》。Java 是 Oracle 和/或其關聯企業的註冊商標。</p> <p>上次更新時間:2025-11-20 (世界標準時間)。</p> </devsite-content-footer> <devsite-notification > </devsite-notification> <div class="devsite-content-data"> <template class="devsite-thumb-rating-feedback"> <devsite-feedback position="thumb-rating" project-name="Cloud Text-to-Speech" product-id="5041938" bucket="Documentation" context="Cloud Text-to-Speech API docs feedback link" version="t-devsite-webserver-20260825-r00-rc00.479916215390653058" data-label="Send Feedback Button" track-type="feedback" track-name="sendFeedbackLink" track-metadata-position="thumb-rating" class="nocontent" data-nosnippet project-feedback-url="https://issuetracker.google.com/issues/new?component=451645" project-icon="https://docs.cloud.google.com/_static/clouddocs/images/icons/categories/ai-and-machine-learning-color.svg?hl=zh-tw" project-support-url="https://docs.cloud.google.com/text-to-speech/docs/support?hl=zh-tw" > <button> 想進一步說明嗎? </button> </devsite-feedback> </template> <template class="devsite-content-data-template"> [[["容易理解","easyToUnderstand","thumb-up"],["確實解決了我的問題","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["難以理解","hardToUnderstand","thumb-down"],["資訊或程式碼範例有誤","incorrectInformationOrSampleCode","thumb-down"],["缺少我需要的資訊/範例","missingTheInformationSamplesINeed","thumb-down"],["翻譯問題","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["上次更新時間:2025-11-20 (世界標準時間)。"],[],[]] </template> </div> </devsite-content> </main> <devsite-footer-promos class="devsite-footer"> </devsite-footer-promos> <devsite-footer-linkboxes class="devsite-footer"> <nav class="devsite-footer-linkboxes nocontent" aria-label="頁尾連結" data-nosnippet> <ul class="devsite-footer-linkboxes-list"> <li class="devsite-footer-linkbox "> <h3 class="devsite-footer-linkbox-heading no-link">產品與定價</h3> <ul class="devsite-footer-linkbox-list"> <li class="devsite-footer-linkbox-item"> <a href="//cloud.google.com/products/?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 1)" track-metadata-eventDetail="cloud.google.com/products/"track-metadata-child_headline="products and pricing"track-type="footer link"track-name="see all products"track-metadata-position="footer"track-metadata-module="footer"> 查看所有產品/服務 </a> </li> <li class="devsite-footer-linkbox-item"> <a href="//cloud.google.com/pricing/?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 2)" track-type="footer link"track-metadata-eventDetail="cloud.google.com/pricing/"track-metadata-position="footer"track-name="google cloud pricing"track-metadata-child_headline="products and pricing"track-metadata-module="footer"> Google Cloud 定價 </a> </li> <li class="devsite-footer-linkbox-item"> <a href="//cloud.google.com/marketplace/?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 3)" track-metadata-child_headline="resources"track-metadata-position="footer"track-metadata-module="footer"track-type="footer link"track-name="google cloud marketplace"track-metadata-eventDetail="cloud.google.com/marketplace/"> Google Cloud Marketplace </a> </li> <li class="devsite-footer-linkbox-item"> <a href="//cloud.google.com/contact/?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 4)" track-metadata-position="footer"track-metadata-module="footer"track-metadata-eventDetail="cloud.google.com/contact/"track-name="contact sales"track-metadata-child_headline="engage"track-type="footer link"> 與銷售人員聯絡 </a> </li> </ul> </li> <li class="devsite-footer-linkbox "> <h3 class="devsite-footer-linkbox-heading no-link">支援服務</h3> <ul class="devsite-footer-linkbox-list"> <li class="devsite-footer-linkbox-item"> <a href="//discuss.google.dev/c/google-cloud/14/?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 1)" track-metadata-child_headline="engage"track-metadata-eventDetail="www.googlecloudcommunity.com"rel="noopener"track-metadata-module="footer"target="_blank"track-type="footer link"track-metadata-position="footer"track-name="google cloud community"> 社群論壇 </a> </li> <li class="devsite-footer-linkbox-item"> <a href="//cloud.google.com/support-hub/?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 2)" track-metadata-child_headline="resources"track-metadata-module="footer"track-metadata-position="footer"track-type="footer link"track-name="support"track-metadata-eventDetail="cloud.google.com/support-hub/"> 支援服務 </a> </li> <li class="devsite-footer-linkbox-item"> <a href="//docs.cloud.google.com/release-notes?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 3)" track-type="footer link"track-metadata-child_headline="resources"track-metadata-module="footer"track-name="release notes"track-metadata-position="footer"track-metadata-eventDetail="cloud.google.com/release-notes/"> 版本資訊 </a> </li> <li class="devsite-footer-linkbox-item"> <a href="//status.cloud.google.com?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 4)" track-metadata-eventDetail="status.cloud.google.com"track-metadata-child_headline="resources"target="_blank"track-metadata-position="footer"track-name="system status"track-metadata-module="footer"track-type="footer link"> 系統狀態 </a> </li> </ul> </li> <li class="devsite-footer-linkbox "> <h3 class="devsite-footer-linkbox-heading no-link">實用資源</h3> <ul class="devsite-footer-linkbox-list"> <li class="devsite-footer-linkbox-item"> <a href="//github.com/googlecloudPlatform/" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 1)" track-metadata-eventDetail="github.com/googlecloudPlatform/"track-metadata-module="footer"track-type="footer link"track-metadata-position="footer"track-name="github"track-metadata-child_headline="resources"> GitHub </a> </li> <li class="devsite-footer-linkbox-item"> <a href="https://docs.cloud.google.com/docs/get-started/?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 2)" track-type="footer link"track-name="google cloud quickstarts"track-metadata-module="footer"track-metadata-position="footer"track-metadata-eventDetail="cloud.google.com/docs/get-started/"track-metadata-child_headline="resources"> 開始使用 Google Cloud </a> </li> <li class="devsite-footer-linkbox-item"> <a href="https://docs.cloud.google.com/docs/samples?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 3)" track-name="code samples"track-type="footer link"track-metadata-position="footer"track-metadata-module="footer"track-metadata-child_headline="resources"track-metadata-eventDetail="cloud.google.com/docs/samples"> 程式碼範例 </a> </li> <li class="devsite-footer-linkbox-item"> <a href="https://docs.cloud.google.com/architecture/?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 4)" track-metadata-module="footer"track-metadata-position="footer"track-metadata-child_headline="resources"track-type="footer link"track-metadata-eventDetail="cloud.google.com/architecture/"track-name="cloud architecture center"> 雲端架構中心 </a> </li> <li class="devsite-footer-linkbox-item"> <a href="//cloud.google.com/learn/training/?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 5)" track-type="footer link"track-name="training"track-metadata-module="footer"track-metadata-position="footer"track-metadata-eventDetail="cloud.google.com/learn/training/"track-metadata-child_headline="resources"> 訓練與認證 </a> </li> </ul> </li> <li class="devsite-footer-linkbox "> <h3 class="devsite-footer-linkbox-heading no-link">互動交流</h3> <ul class="devsite-footer-linkbox-list"> <li class="devsite-footer-linkbox-item"> <a href="//cloud.google.com/blog/?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 1)" track-type="footer link"track-metadata-eventDetail="cloud.google.com/blog/"track-name="blog"track-metadata-position="footer"track-metadata-child_headline="engage"track-metadata-module="footer"> 網誌 </a> </li> <li class="devsite-footer-linkbox-item"> <a href="//cloud.google.com/events/?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 2)" track-metadata-module="footer"track-metadata-position="footer"track-metadata-eventDetail="cloud.google.com/events/"track-name="events"track-type="footer link"track-metadata-child_headline="engage"> 活動 </a> </li> <li class="devsite-footer-linkbox-item"> <a href="//x.com/googlecloud" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 3)" track-metadata-eventDetail="x.com/googlecloud"target="_blank"rel="noopener"track-type="footer link"track-metadata-module="footer"track-metadata-position="footer"track-name="follow on x"track-metadata-child_headline="engage"> X (Twitter) </a> </li> <li class="devsite-footer-linkbox-item"> <a href="//www.youtube.com/googlecloud?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 4)" track-metadata-child_headline="engage"rel="noopener"track-type="footer link"track-metadata-module="footer"track-metadata-eventDetail="www.youtube.com/googlecloud"track-name="google cloud on youtube"target="_blank"track-metadata-position="footer"> Google Cloud 的 YouTube 頻道 </a> </li> <li class="devsite-footer-linkbox-item"> <a href="//www.youtube.com/googlecloudplatform?hl=zh-tw" class="devsite-footer-linkbox-link gc-analytics-event" data-category="Site-Wide Custom Events" data-label="Footer Link (index 5)" track-metadata-module="footer"track-metadata-child_headline="engage"track-metadata-position="footer"track-type="footer link"track-name="google cloud tech on youtube"rel="noopener"target="_blank"track-metadata-eventDetail="www.youtube.com/googlecloudplatform"> Google Cloud Tech 的 YouTube 頻道 </a> </li> </ul> </li> </ul> </nav> </devsite-footer-linkboxes> <devsite-footer-utility class="devsite-footer"> <div class="devsite-footer-utility nocontent" data-nosnippet> <nav class="devsite-footer-utility-links" aria-label="公用程式連結"> <ul class="devsite-footer-utility-list"> <li class="devsite-footer-utility-item "> <a class="devsite-footer-utility-link gc-analytics-event" href="//about.google/intl/zh-tw/?hl=zh-tw" data-category="Site-Wide Custom Events" data-label="Footer About Google link" track-metadata-eventDetail="//about.google/" track-metadata-position="footer" target="_blank" track-type="footer link" track-metadata-module="utility footer" track-name="about google" > 關於 Google </a> </li> <li class="devsite-footer-utility-item devsite-footer-privacy-link"> <a class="devsite-footer-utility-link gc-analytics-event" href="//policies.google.com/privacy?hl=zh-TW" data-category="Site-Wide Custom Events" data-label="Footer Privacy link" track-name="privacy" track-type="footer link" track-metadata-position="footer" track-metadata-eventDetail="//policies.google.com/privacy" target="_blank" track-metadata-module="utility footer" > 隱私權 </a> </li> <li class="devsite-footer-utility-item "> <a class="devsite-footer-utility-link gc-analytics-event" href="//policies.google.com/terms?hl=zh-tw" data-category="Site-Wide Custom Events" data-label="Footer Site terms link" track-name="site terms" track-metadata-position="footer" target="_blank" track-type="footer link" track-metadata-eventDetail="//www.google.com/intl/en/policies/terms/regional.html" track-metadata-module="utility footer" > 網站條款 </a> </li> <li class="devsite-footer-utility-item "> <a class="devsite-footer-utility-link gc-analytics-event" href="//cloud.google.com/product-terms?hl=zh-tw" data-category="Site-Wide Custom Events" data-label="Footer Google Cloud terms link" track-metadata-position="footer" track-type="footer link" track-metadata-module="utility footer" track-name="google cloud terms" track-metadata-eventDetail="//cloud.google.com/product-terms" > Google Cloud 服務條款 </a> </li> <li class="devsite-footer-utility-item glue-cookie-notification-bar-control"> <a class="devsite-footer-utility-link gc-analytics-event" href="#" data-category="Site-Wide Custom Events" data-label="Footer Manage cookies link" track-metadata-module="utility footer" track-metadata-position="footer" track-name="Manage cookies" track-metadata-eventDetail="#" aria-hidden="true" track-type="footer link" > Manage cookies </a> </li> <li class="devsite-footer-utility-item devsite-footer-carbon-button"> <a class="devsite-footer-utility-link gc-analytics-event" href="//cloud.google.com/sustainability?hl=zh-tw" data-category="Site-Wide Custom Events" data-label="Footer Our third decade of climate action: join us link" track-metadata-eventDetail="/sustainability/" track-name="Our third decade of climate action: join us" track-type="footer link" track-metadata-position="footer" track-metadata-module="utility footer" > 我們的第三個十年氣候計畫:加入我們 </a> </li> <li class="devsite-footer-utility-item devsite-footer-utility-button"> <span class="devsite-footer-utility-description">訂閱 Google Cloud 電子報</span> <a class="devsite-footer-utility-link gc-analytics-event" href="//cloud.google.com/newsletter/?hl=zh-tw" data-category="Site-Wide Custom Events" data-label="Footer Subscribe link" track-metadata-position="footer" track-metadata-eventDetail="/newsletter/" track-type="footer link" track-metadata-module="utility footer" track-name="subscribe" > 訂閱 </a> </li> </ul> <devsite-language-selector> <ul role="presentation"> <li role="presentation"> <a role="menuitem" lang="en" >English</a> </li> <li role="presentation"> <a role="menuitem" lang="de" >Deutsch</a> </li> <li role="presentation"> <a role="menuitem" lang="es" >Español</a> </li> <li role="presentation"> <a role="menuitem" lang="es_419" >Español – América Latina</a> </li> <li role="presentation"> <a role="menuitem" lang="fr" >Français</a> </li> <li role="presentation"> <a role="menuitem" lang="id" >Indonesia</a> </li> <li role="presentation"> <a role="menuitem" lang="it" >Italiano</a> </li> <li role="presentation"> <a role="menuitem" lang="pt" >Português</a> </li> <li role="presentation"> <a role="menuitem" lang="pt_br" >Português – Brasil</a> </li> <li role="presentation"> <a role="menuitem" lang="he" >עברית</a> </li> <li role="presentation"> <a role="menuitem" lang="zh_cn" >中文 – 简体</a> </li> <li role="presentation"> <a role="menuitem" lang="zh_tw" >中文 – 繁體</a> </li> <li role="presentation"> <a role="menuitem" lang="ja" >日本語</a> </li> <li role="presentation"> <a role="menuitem" lang="ko" >한국어</a> </li> </ul> </devsite-language-selector> </nav> </div> </devsite-footer-utility> <devsite-panel> </devsite-panel> </section> </section> <devsite-sitemask></devsite-sitemask> <devsite-snackbar></devsite-snackbar> <devsite-tooltip ></devsite-tooltip> <devsite-heading-link></devsite-heading-link> <devsite-analytics> <script type="application/json" analytics>[]</script> <script type="application/json" tag-management>{"at": "True", "ga4": [], "ga4p": [], "gtm": [{"id": "GTM-5CVQBG", "purpose": 1}], "parameters": {"internalUser": "False", "language": {"machineTranslated": "False", "requested": "zh-tw", "served": "zh-tw"}, "pageType": "article", "projectName": "Cloud Text-to-Speech", "signedIn": "False", "tenant": "clouddocs", "recommendations": {"sourcePage": "", "sourceType": 0, "sourceRank": 0, "sourceIdenticalDescriptions": 0, "sourceTitleWords": 0, "sourceDescriptionWords": 0, "experiment": ""}, "experiment": {"ids": ""}}}</script> </devsite-analytics> <devsite-badger></devsite-badger> <cloudx-user></cloudx-user> <cloudx-free-trial-eligible-store freeTrialEligible="true"></cloudx-free-trial-eligible-store> <script nonce="UEkl9UB9k/YxC8vZMM2yhnyfz+OSBI"> (function(d,e,v,s,i,t,E){d['GoogleDevelopersObject']=i; t=e.createElement(v);t.async=1;t.src=s;E=e.getElementsByTagName(v)[0]; E.parentNode.insertBefore(t,E);})(window, document, 'script', 'https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/clouddocs/js/app_loader.js', '[39,"zh_tw",null,"/js/devsite_app_module.js","https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e","https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/clouddocs","https://clouddocs-dot-devsite-v2-prod.appspot.com",null,null,["/_pwa/clouddocs/manifest.json","https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/images/video-placeholder.svg","https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/clouddocs/images/favicons/onecloud/favicon.ico","https://www.gstatic.com/devrel-devsite/prod/vdc800838fb8be04a9a7685606311d18c65800504bccf261551968ac74bffd42e/clouddocs/images/lockup_full_color.svg","https://fonts.googleapis.com/css?family=Google+Sans:400,500|Roboto:400,400italic,500,500italic,700,700italic|Roboto+Mono:400,500,700&display=swap"],1,null,[1,6,8,12,14,17,21,25,50,52,63,70,75,76,80,87,91,92,93,97,98,100,101,102,103,104,105,107,108,109,110,112,113,117,118,120,122,124,125,126,127,129,130,131,132,133,134,135,136,138,140,141,147,148,149,151,152,156,157,158,159,161,163,164,168,169,170,179,180,182,183,186,191,193,196],"AIzaSyAP-jjEJBzmIyKR4F-3XITp8yM9T1gEEI8","AIzaSyB6xiKGDR5O3Ak2okS4rLkauxGUG7XP0hg","docs.cloud.google.com","AIzaSyAQk0fBONSGUqCNznf6Krs82Ap1-NV6J4o","AIzaSyCCxcqdrZ_7QMeLCRY20bh_SXdAYqy70KY",null,null,null,["OnSwitch__enable","DevPro__enable_embed_profile_creation","DevPro__enable_code_assist","TpcFeatures__proxy_prod_host","Cloud__enable_cloud_shell_fte_user_flow","Cloud__enable_free_trial_server_call","MiscFeatureFlags__enable_variable_operator","MiscFeatureFlags__enable_appearance_cookies","Cloud__cache_serialized_dynamic_content","MiscFeatureFlags__enable_firebase_utm","Concierge__enable_devsite_llm_tools","DevPro__enable_devsite_captcha","DevPro__enable_nvidia_credits_card","DevPro__enable_free_benefits","Profiles__enable_completequiz_endpoint","Search__enable_dynamic_content_confidential_banner","CloudShell__cloud_code_overflow_menu","DevPro__remove_eu_tax_intake_form","DevPro__enable_enterprise","Profiles__enable_stripe_subscription_management","Profiles__enable_auto_apply_credits","Concierge__enable_pushui","Search__enable_suggestions_from_borg","MiscFeatureFlags__developers_footer_dark_image","SignIn__enable_l1_signup_flow","Concierge__enable_concierge_restricted","Analytics__enable_clearcut_logging","DevPro__enable_devpro_offers","Cloud__enable_legacy_calculator_redirect","Profiles__enable_complete_playlist_endpoint","Profiles__enable_targeted_hero","AIStudioInteractionsToggle__interactions_are_default","MiscFeatureFlags__enable_dark_theme","MiscFeatureFlags__enable_explicit_template_dependencies","DevPro__enable_developer_subscriptions","BookNav__enable_tenant_cache_key","Profiles__enable_developer_profile_benefits_ui_redesign","Search__enable_page_map","Profiles__enable_developer_profile_pages_as_content","MiscFeatureFlags__enable_view_transitions","DevPro__enable_g1_ineligible_redirect","MiscFeatureFlags__remove_cross_domain_tracking_params","Search__enable_ai_search_summaries_for_all","DevPro__enable_firebase_workspaces_card","Search__enable_ai_eligibility_checks","Cloud__enable_cloud_shell","MiscFeatureFlags__enable_variable_operator_index_yaml","MiscFeatureFlags__fix_lower_breadcrumbs","MiscFeatureFlags__enable_project_variables","Concierge__enable_actions_menu","MiscFeatureFlags__developers_footer_image","CloudShell__cloud_shell_button","EngEduTelemetry__enable_engedu_telemetry","Profiles__enable_developer_profiles_callout","Analytics__enable_devpro_interaction_logging","Profiles__enable_dashboard_curated_recommendations","Profiles__require_profile_eligibility_for_signin","Profiles__enable_awarding_url","DevPro__enable_credits_banner","Profiles__enable_playlist_community_acl","MiscFeatureFlags__gdp_dashboard_reskin_enabled","DevPro__enable_google_one_card","Profiles__enable_purchase_prompts","MiscFeatureFlags__enable_explain_this_code","Profiles__enable_page_saving","DevPro__enable_google_payments_buyflow","DevPro__enable_google_payments","MiscFeatureFlags__enable_framebox_badge_methods","Cloud__enable_cloudx_experiment_ids","Profiles__enable_completecodelab_endpoint","DevPro__enable_cloud_innovators_plus","Concierge__enable_remove_info_panel_tags","Profiles__enable_callout_notifications","Experiments__reqs_query_experiments","Profiles__enable_join_program_group_endpoint","DevPro__enable_g1_integration","Profiles__enable_profile_collections","Profiles__enable_user_type","Profiles__enable_public_developer_profiles","Cloud__enable_cloud_dlp_service","DevPro__enable_vertex_credit_card","Profiles__enable_recognition_badges","TpcFeatures__enable_unmirrored_page_left_nav","Cloud__fast_free_trial"],null,null,"AIzaSyBLEMok-5suZ67qRPzx0qUtbnLmyT_kCVE","https://developerscontentserving-pa.clients6.google.com","AIzaSyCM4QpTRSqP5qI4Dvjt4OAScIN8sOUlO-k","https://developerscontentsearch-pa.clients6.google.com",1,4,1,"https://developerprofiles-pa.clients6.google.com",[39,"clouddocs","Google Cloud Documentation","docs.cloud.google.com",null,"clouddocs-dot-devsite-v2-prod.appspot.com",null,null,[1,1,null,null,null,null,null,null,null,null,null,[1],null,null,null,null,null,1,[1],[null,null,null,[1,20],"/terms/recommendations"],[1],null,[1],[1,null,1],null,[1]],null,[54,null,null,null,null,null,"/images/lockup_full_color.svg","/images/favicons/onecloud/apple-icon.png",null,null,null,1,1,1,1,null,[],null,null,[[],[],[],[],[],[],[],[]],null,1,null,null,null,"/images/lockup_dark_theme.svg",[]],[],null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,[6,1,14,15,22,23,29,37],null,[[null,null,null,null,null,null,[1,[["docType","Choose a content type",[["ApiReference",null,null,null,null,null,null,null,null,"API reference"],["Sample",null,null,null,null,null,null,null,null,"Code sample"],["ReferenceArchitecture",null,null,null,null,null,null,null,null,"Reference architecture"],["Tutorial",null,null,null,null,null,null,null,null,"Tutorial"]]],["category","Choose a topic",[["AiAndMachineLearning",null,null,null,null,null,null,null,null,"Artificial intelligence and machine learning (AI/ML)"],["ApplicationDevelopment",null,null,null,null,null,null,null,null,"Application development"],["BigDataAndAnalytics",null,null,null,null,null,null,null,null,"Big data and analytics"],["Compute",null,null,null,null,null,null,null,null,"Compute"],["Containers",null,null,null,null,null,null,null,null,"Containers"],["Databases",null,null,null,null,null,null,null,null,"Databases"],["HybridCloud",null,null,null,null,null,null,null,null,"Hybrid and multicloud"],["LoggingAndMonitoring",null,null,null,null,null,null,null,null,"Logging and monitoring"],["Migrations",null,null,null,null,null,null,null,null,"Migrations"],["Networking",null,null,null,null,null,null,null,null,"Networking"],["SecurityAndCompliance",null,null,null,null,null,null,null,null,"Security and compliance"],["Serverless",null,null,null,null,null,null,null,null,"Serverless"],["Storage",null,null,null,null,null,null,null,null,"Storage"]]]]]],[1],null,1],[[null,null,null,null,null,["GTM-5CVQBG"],null,null,null,null,null,[["GTM-5CVQBG",2]],1],null,null,null,null,null,1],"mwETRvWii0eU5NUYprb0Y9z5GVbc",4],null,"pk_live_5170syrHvgGVmSx9sBrnWtA5luvk9BwnVcvIi7HizpwauFG96WedXsuXh790rtij9AmGllqPtMLfhe2RSwD6Pn38V00uBCydV4m",1,1,"https://developerscontentinsights-pa.clients6.google.com","AIzaSyCg-ZUslalsEbXMfIo9ZP8qufZgo3LSBDU","AIzaSyDxT0vkxnY_KeINtA4LSePJO-4MAZPMRsE","https://developers.clients6.google.com",null,null,"AIzaSyBQom12tzI-rybN7Sf-KfeL4nwm-Rf7PmI\n",null,null,"https://developers.googleapis.com"]') </script> <devsite-a11y-announce></devsite-a11y-announce> </body> </html>
Model input reference derived from preset schema.
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
| text | string | Yes | null | Text to speak. You can include natural-language direction for style, accent, pace, and emotion. |
| voice_2 | select | No | "Puck" | Voice used for speaker 2 when both speaker names are provided. |
| voice_name | select | Yes | "Kore" | Prebuilt voice used for single-speaker output or speaker 1. |
| speaker_1_name | string | No | null | For two-speaker output, enter the first speaker name exactly as written in the transcript. |
| speaker_2_name | string | No | null | Enter the second speaker name exactly as written in the transcript. |