{"id":22953,"date":"2026-07-31T19:09:01","date_gmt":"2026-07-31T19:09:01","guid":{"rendered":"https:\/\/scannn.com\/gemini-live-api-overview-gemini-api-google-ai-for-developers\/"},"modified":"2026-07-31T19:09:01","modified_gmt":"2026-07-31T19:09:01","slug":"gemini-live-api-overview-gemini-api-google-ai-for-developers","status":"publish","type":"post","link":"https:\/\/scannn.com\/lv\/gemini-live-api-overview-gemini-api-google-ai-for-developers\/","title":{"rendered":"Gemini Live API overview \u00a0|\u00a0 Gemini API \u00a0|\u00a0 Google AI for Developers"},"content":{"rendered":"\n<div id=\"main-content\">\n<p>          <devsite-content><\/p>\n<article class=\"devsite-article\">\n<div class=\"devsite-banner devsite-banner-announcement nocontent\" data-nosnippet=\"\" background=\"google-blue\">\n<div class=\"devsite-banner-message\">\n<div class=\"devsite-banner-message-text\">\n          The <a href=\"https:\/\/ai.google.dev\/gemini-api\/docs\/interactions-overview\" style=\"color: black;\">Interactions API<\/a> is now generally available. We recommend using this API for access to all the latest features and models.\n        <\/div>\n<\/p><\/div>\n<\/p><\/div>\n<p>    <devsite-feedback position=\"header\" project-name=\"Gemini API\" product-id=\"5292923\" bucket=\"documentation\" context=\"\" version=\"t-devsite-webserver-20260728-r00-rc02.479288207165724890\" data-label=\"Send Feedback Button\" track-type=\"feedback\" track-name=\"sendFeedbackLink\" track-metadata-position=\"header\" class=\"nocontent\" data-nosnippet=\"\" project-icon=\"https:\/\/www.gstatic.com\/devrel-devsite\/prod\/vf667a9fd586ec573473a76e7c76b3edb8ab0c1db42d0ede8e8f66ff6cc9d7f08\/googledevai\/images\/touchicon-180-new.png\"><\/p>\n<p>  <button><\/p>\n<p>    Send feedback<\/p>\n<p>  <\/button><br \/>\n<\/devsite-feedback><\/p>\n<p>  <devsite-toc class=\"devsite-nav\" depth=\"2\" devsite-toc-embedded=\"\"><br \/>\n  <\/devsite-toc><\/p>\n<div class=\"devsite-article-body clearfix&#10;  \">\n<aside class=\"preview\"><strong>Preview:<\/strong><span> The Live API is in<br \/>\n<a href=\"https:\/\/cloud.google.com\/products#product-launch-stages\">Preview<\/a>.<\/span><\/aside>\n<p>The Live API enables low-latency, real-time voice and vision interactions with<br \/>\nGemini. It processes continuous streams of audio, images, and text to deliver<br \/>\nimmediate, human-like spoken responses, creating a natural conversational<br \/>\nexperience for your users.<\/p>\n<p><\/p>\n<h2 id=\"use-cases\" data-text=\"Use cases\" tabindex=\"-1\">Use cases<\/h2>\n<p>Live API can be used to build real-time voice agents for a<br \/>\nvariety of industries, including:<\/p>\n<ul>\n<li><strong>E-commerce and retail:<\/strong> Shopping assistants that offer personalized<br \/>\nrecommendations and support agents that resolve customer issues.<\/li>\n<li><strong>Gaming:<\/strong> Interactive non-player characters (NPCs), in-game help<br \/>\nassistants, and real-time translation of in-game content.<\/li>\n<li><strong>Next-gen interfaces:<\/strong> Voice- and video-enabled experiences in robotics,<br \/>\nsmart glasses, and vehicles.<\/li>\n<li><strong>Healthcare:<\/strong> Health companions for patient support and education.<\/li>\n<li><strong>Financial services:<\/strong> AI advisors for wealth management and investment<br \/>\nguidance.<\/li>\n<li><strong>Education:<\/strong> AI mentors and learner companions that provide personalized<br \/>\ninstruction and feedback.<\/li>\n<li><strong>Translation and localization:<\/strong> Real-time, low-latency translation of<br \/>\nspoken conversations, enabling seamless multilingual communication.<\/li>\n<\/ul>\n<h2 id=\"key-features\" data-text=\"Key features\" tabindex=\"-1\">Key features<\/h2>\n<p>Live API offers a comprehensive set of features for building<br \/>\nrobust voice agents:<\/p>\n<ul>\n<li><a href=\"http:\/\/ai.google.dev\/gemini-api\/docs\/live-guide#supported-languages\"><strong>Multilingual support<\/strong><\/a>:<br \/>\nConverse in 70 supported languages.<\/li>\n<li><a href=\"http:\/\/ai.google.dev\/gemini-api\/docs\/live-guide#interruptions\"><strong>Barge-in<\/strong><\/a>:<br \/>\nUsers can interrupt the model at any time for responsive interactions.<\/li>\n<li><a href=\"https:\/\/ai.google.dev\/gemini-api\/docs\/live-tools\"><strong>Tool use<\/strong><\/a>:<br \/>\nIntegrates tools like function calling and Google Search for dynamic<br \/>\ninteractions.<\/li>\n<li><a href=\"http:\/\/ai.google.dev\/gemini-api\/docs\/live-guide#audio-transcription\"><strong>Audio transcriptions<\/strong><\/a>:<br \/>\nProvides text transcripts of both user input and model output.<\/li>\n<li><a href=\"http:\/\/ai.google.dev\/gemini-api\/docs\/live-guide#proactive-audio\"><strong>Proactive audio<\/strong><\/a>:<br \/>\nLets you control when the model responds and in what contexts.<\/li>\n<li><a href=\"http:\/\/ai.google.dev\/gemini-api\/docs\/live-guide#affective-dialog\"><strong>Affective dialog<\/strong><\/a>:<br \/>\nAdapts response style and tone to match the user&#8217;s input expression.<\/li>\n<li><a href=\"https:\/\/ai.google.dev\/gemini-api\/docs\/live-api\/live-translate\"><strong>Live Translation<\/strong><\/a>:<br \/>\nReal-time voice-to-voice translation in 70+ languages.<\/li>\n<\/ul>\n<h2 id=\"technical-specifications\" data-text=\"Technical specifications\" tabindex=\"-1\">Technical specifications<\/h2>\n<p>The following table outlines the technical specifications for the<br \/>\nLive API:<\/p>\n<table>\n<thead>\n<tr>\n<th style=\"text-align: left\">Category<\/th>\n<th style=\"text-align: left\">Details<\/th>\n<\/tr>\n<\/thead>\n<tbody>\n<tr>\n<td style=\"text-align: left\">Input modalities<\/td>\n<td style=\"text-align: left\">Audio (raw 16-bit PCM audio, 16kHz, little-endian), images (JPEG &lt;= 1FPS), text<\/td>\n<\/tr>\n<tr>\n<td style=\"text-align: left\">Output modalities<\/td>\n<td style=\"text-align: left\">Audio (raw 16-bit PCM audio, 24kHz, little-endian)<\/td>\n<\/tr>\n<tr>\n<td style=\"text-align: left\">Protocol<\/td>\n<td style=\"text-align: left\">Stateful WebSocket connection (WSS)<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<h2 id=\"implementation-approach\" data-text=\"Choose an implementation approach\" tabindex=\"-1\">Choose an implementation approach<\/h2>\n<p>When integrating with Live API, you&#8217;ll need to choose one of the following<br \/>\nimplementation approaches:<\/p>\n<ul>\n<li><strong>Server-to-server<\/strong>: Your backend connects to the Live API using<br \/>\n<a href=\"https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/WebSockets_API\">WebSockets<\/a>. Typically, your client sends stream data (audio, video,<br \/>\ntext) to your server, which then forwards it to the Live API.<\/li>\n<li><strong>Client-to-server<\/strong>: Your frontend code connects directly to the Live API<br \/>\nusing <a href=\"https:\/\/developer.mozilla.org\/en-US\/docs\/Web\/API\/WebSockets_API\">WebSockets<\/a> to stream data, bypassing your backend.<\/li>\n<\/ul>\n<aside class=\"note\"><strong>Note:<\/strong><span> Client-to-server generally offers better performance for streaming audio<br \/>\nand video, since it bypasses the need to send the stream to your backend first.<br \/>\nIt&#8217;s also easier to set up since you don&#8217;t need to implement a proxy that sends<br \/>\ndata from your client to your server and then your server to the API. However,<br \/>\nfor production environments, in order to mitigate security risks, we recommend<br \/>\nusing <a href=\"https:\/\/ai.google.dev\/gemini-api\/docs\/ephemeral-tokens\">ephemeral tokens<\/a> instead of standard<br \/>\nAPI keys.<\/span><\/aside>\n<h2 id=\"get-started\" data-text=\"Get started\" tabindex=\"-1\">Get started<\/h2>\n<p>Select the guide that matches your development environment:<\/p>\n<div class=\"devsite-card-group\">\n<div class=\"devsite-card-wrapper\">\n<div class=\"devsite-card\">\n<div class=\"devsite-card-content-wrapper\">\n<div class=\"devsite-card-content\">\n<p>  <span class=\"devsite-label\"><\/p>\n<p>      Server-to-server<\/p>\n<p>  <\/span><\/p>\n<h3 class=\"hide-from-toc no-link\" id=\"genai-sdk-tutorial\" data-text=\"                                                      GenAI SDK tutorial                                                    \" tabindex=\"-1\">\n<p>              <a href=\"https:\/\/ai.google.dev\/gemini-api\/docs\/live-api\/get-started-sdk\" track-metadata-eventdetail=\"get-started-sdk\" track-type=\"card\" track-name=\"&#10;  GenAI SDK tutorial&#10;\" track-metadata-child_headline=\"GenAI SDK tutorial\" track-metadata-child_chip_label=\"Server-to-server\"><\/p>\n<p>            GenAI SDK tutorial<\/p>\n<p>              <\/a><\/p>\n<\/h3>\n<p class=\"devsite-card-summary\">\n<p>            Connect to the Gemini Live API using the GenAI SDK to build a real-time multimodal application with a Python backend.<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<\/p><\/div>\n<\/div>\n<div class=\"devsite-card-wrapper\">\n<div class=\"devsite-card\">\n<div class=\"devsite-card-content-wrapper\">\n<div class=\"devsite-card-content\">\n<p>  <span class=\"devsite-label\"><\/p>\n<p>      Client-to-server<\/p>\n<p>  <\/span><\/p>\n<h3 class=\"hide-from-toc no-link\" id=\"websocket-tutorial\" data-text=\"                                                      WebSocket tutorial                                                    \" tabindex=\"-1\">\n<p>              <a href=\"https:\/\/ai.google.dev\/gemini-api\/docs\/live-api\/get-started-websocket\" track-metadata-eventdetail=\"get-started-websocket\" track-type=\"card\" track-name=\"&#10;  WebSocket tutorial&#10;\" track-metadata-child_headline=\"WebSocket tutorial\" track-metadata-child_chip_label=\"Client-to-server\"><\/p>\n<p>            WebSocket tutorial<\/p>\n<p>              <\/a><\/p>\n<\/h3>\n<p class=\"devsite-card-summary\">\n<p>            Connect to the Gemini Live API using WebSockets to build a real-time multimodal application with a JavaScript frontend and ephemeral tokens.<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<\/p><\/div>\n<\/div>\n<div class=\"devsite-card-wrapper\">\n<div class=\"devsite-card\">\n<div class=\"devsite-card-content-wrapper\">\n<div class=\"devsite-card-content\">\n<p>  <span class=\"devsite-label\"><\/p>\n<p>      Agent development kit<\/p>\n<p>  <\/span><\/p>\n<h3 class=\"hide-from-toc no-link\" id=\"adk-tutorial\" data-text=\"                                                      ADK tutorial                                                    \" tabindex=\"-1\">\n<p>              <a href=\"https:\/\/google.github.io\/adk-docs\/streaming\/\" track-metadata-eventdetail=\"https:\/\/google.github.io\/adk-docs\/streaming\/\" track-type=\"card\" track-name=\"&#10;  ADK tutorial&#10;\" track-metadata-child_headline=\"ADK tutorial\" track-metadata-child_chip_label=\"Agent Development Kit\"><\/p>\n<p>            ADK tutorial<\/p>\n<p>              <\/a><\/p>\n<\/h3>\n<p class=\"devsite-card-summary\">\n<p>            Create an agent and use the Agent Development Kit (ADK) Streaming to enable voice and video communication.<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<\/p><\/div>\n<\/div>\n<\/div>\n<div class=\"main-content\">\n<h2 id=\"partner-integrations\" data-text=\"Partner integrations\" tabindex=\"-1\">Partner integrations<\/h2>\n<p>\n    To streamline the development of real-time audio and video apps, you can use<br \/>\n    a third-party integration that supports the Gemini Live<br \/>\n    API over WebRTC or WebSockets.\n  <\/p>\n<\/div>\n<link href=\"https:\/\/fonts.googleapis.com\/css2?family=Google+Symbols:opsz,wght,FILL,GRAD@20..48,100..700,0..1,-50..200\" rel=\"stylesheet\" data-page-link=\"\"\/>\n<\/div>\n<p>    <devsite-thumb-rating position=\"footer\"><br \/>\n    <\/devsite-thumb-rating><\/p>\n<p>         <devsite-feedback position=\"footer\" project-name=\"Gemini API\" product-id=\"5292923\" bucket=\"documentation\" context=\"\" version=\"t-devsite-webserver-20260728-r00-rc02.479288207165724890\" data-label=\"Send Feedback Button\" track-type=\"feedback\" track-name=\"sendFeedbackLink\" track-metadata-position=\"footer\" class=\"nocontent\" data-nosnippet=\"\" project-icon=\"https:\/\/www.gstatic.com\/devrel-devsite\/prod\/vf667a9fd586ec573473a76e7c76b3edb8ab0c1db42d0ede8e8f66ff6cc9d7f08\/googledevai\/images\/touchicon-180-new.png\"><\/p>\n<p>  <button><\/p>\n<p>    Send feedback<\/p>\n<p>  <\/button><br \/>\n<\/devsite-feedback><\/p>\n<\/article>\n<p><devsite-content-footer class=\"nocontent\" data-nosnippet=\"\"><\/p>\n<p>Except as otherwise noted, the content of this page is licensed under the <a href=\"https:\/\/creativecommons.org\/licenses\/by\/4.0\/\">Creative Commons Attribution 4.0 License<\/a>, and code samples are licensed under the <a href=\"https:\/\/www.apache.org\/licenses\/LICENSE-2.0\">Apache 2.0 License<\/a>. For details, see the <a href=\"https:\/\/developers.google.com\/site-policies\">Google Developers Site Policies<\/a>. Java is a registered trademark of Oracle and\/or its affiliates.<\/p>\n<p>Last updated 2026-06-12 UTC.<\/p>\n<p><\/devsite-content-footer><\/p>\n<p><devsite-notification><br \/>\n<\/devsite-notification><\/p>\n<p>    <template class=\"devsite-thumb-rating-feedback\"><br \/>\n      <devsite-feedback position=\"thumb-rating\" project-name=\"Gemini API\" product-id=\"5292923\" bucket=\"documentation\" context=\"\" version=\"t-devsite-webserver-20260728-r00-rc02.479288207165724890\" data-label=\"Send Feedback Button\" track-type=\"feedback\" track-name=\"sendFeedbackLink\" track-metadata-position=\"thumb-rating\" class=\"nocontent\" data-nosnippet=\"\" project-icon=\"https:\/\/www.gstatic.com\/devrel-devsite\/prod\/vf667a9fd586ec573473a76e7c76b3edb8ab0c1db42d0ede8e8f66ff6cc9d7f08\/googledevai\/images\/touchicon-180-new.png\"><\/p>\n<p>  <button><\/p>\n<p>    Need to tell us more?<\/p>\n<p>  <\/button><br \/>\n<\/devsite-feedback><br \/>\n    <\/template><\/p>\n<p>    <template class=\"devsite-content-data-template\"><br \/>\n      [[[&#8220;Easy to understand&#8221;,&#8221;easyToUnderstand&#8221;,&#8221;thumb-up&#8221;],[&#8220;Solved my problem&#8221;,&#8221;solvedMyProblem&#8221;,&#8221;thumb-up&#8221;],[&#8220;Other&#8221;,&#8221;otherUp&#8221;,&#8221;thumb-up&#8221;]],[[&#8220;Missing the information I need&#8221;,&#8221;missingTheInformationINeed&#8221;,&#8221;thumb-down&#8221;],[&#8220;Too complicated \/ too many steps&#8221;,&#8221;tooComplicatedTooManySteps&#8221;,&#8221;thumb-down&#8221;],[&#8220;Out of date&#8221;,&#8221;outOfDate&#8221;,&#8221;thumb-down&#8221;],[&#8220;Samples \/ code issue&#8221;,&#8221;samplesCodeIssue&#8221;,&#8221;thumb-down&#8221;],[&#8220;Other&#8221;,&#8221;otherDown&#8221;,&#8221;thumb-down&#8221;]],[&#8220;Last updated 2026-06-12 UTC.&#8221;],[],[]]<br \/>\n    <\/template><\/p>\n<p>          <\/devsite-content>\n        <\/div>\n<p><a href=\"https:\/\/ai.google.dev\/gemini-api\/docs\/live-api?linkId=63011869&amp;utm_source=tldrai\">Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The Interactions API is now generally available. We recommend using this API for access to all the latest features and models. Send feedback Preview: The Live API is in Preview. The Live API enables low-latency, real-time voice and vision interactions with Gemini. It processes continuous streams of audio, images, and text to deliver immediate, human-like [&hellip;]<\/p>\n","protected":false},"author":16,"featured_media":22954,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[143],"tags":[],"class_list":["post-22953","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai"],"_links":{"self":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/posts\/22953","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/users\/16"}],"replies":[{"embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/comments?post=22953"}],"version-history":[{"count":0,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/posts\/22953\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/media\/22954"}],"wp:attachment":[{"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/media?parent=22953"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/categories?post=22953"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/scannn.com\/lv\/wp-json\/wp\/v2\/tags?post=22953"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}