--- title: Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking description: Google announced two new Gemini audio models, Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, aimed at powering real-time voice agents and more natural... canonical: https://daily.dev/posts/introducing-gemini-3-8-live-and-3-8-live-extended-thinking-cicfsv9uc twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking | daily.dev og:description: Google announced two new Gemini audio models, Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, aimed at powering real-time voice agents and more natural... og:url: https://daily.dev/posts/introducing-gemini-3-8-live-and-3-8-live-extended-thinking-cicfsv9uc og:image: https://api.daily.dev/og/posts/CIcfsV9uc.png og:image:alt: Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking **[DeepMind](https://daily.dev/sources/dm)** · 4 min read · 0 upvotes · 0 comments ## Summary Google announced two new Gemini audio models, Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, aimed at powering real-time voice agents and more natural spoken interactions. The Extended Thinking variant leads several speech benchmarks including Artificial Analysis' Speech to Speech Quality Index, τ-Voice agentic tasks, and Big Bench Audio, while Gemini 3.8 Live ranks second in the Speech Agent Arena and focuses on cost efficiency at scale. Both models support near real-time visual grounding, automatic language switching across 97 languages, and background tool execution during conversations. Developer platforms like Agora, LiveKit, Pipecat, Vercel, and LangChain already integrate the Gemini Live API. All generated audio is watermarked with SynthID. The models are rolling out now via the Gemini API, Google AI Studio, Gemini Enterprise (private preview), Search Live, Gemini app, and Google Workspace. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Gemini 3.8 Live Extended Thinking and how does it perform on voice benchmarks? Gemini 3.8 Live Extended Thinking is a Google voice model built for high-complexity, multi-step reasoning tasks in real-time conversation. It ranks first on Artificial Analysis' Speech to Speech Quality Index with a score of 82.6, scores 68.6% on τ-Voice and 35.1% on Sierra's τ-Voice-banking benchmark, and reaches 97.7% on Big Bench Audio. _Developers evaluating voice agent models can track benchmark comparisons like these on daily.dev._ ### How can I integrate Gemini Live API into a voice agent application? The Gemini Live API can be integrated through developer platforms including Agora, Fishjam, LangChain, LiveKit, Pipecat, Vercel, and Vision Agents, which handle real-time media streaming infrastructure so developers can focus on the user experience. It's available in the Gemini API and Google AI Studio, with enterprise access in private preview via Gemini Enterprise. _Developers building voice-driven apps follow API and platform integration news like this on daily.dev._ ### How does Gemini 3.8 Live handle multiple languages and background tasks during a conversation? Gemini 3.8 Live automatically detects and switches between 97 supported languages mid-conversation without interruption. It also executes tool calls and API requests in the background while continuing the dialogue, acknowledging user requests and keeping the conversation flowing while tasks complete asynchronously. _Teams building multilingual voice agents can follow model capability updates like this on daily.dev._ ## Similar posts on daily.dev - [Improved Gemini audio models for powerful voice interactions](https://daily.dev/posts/improved-gemini-audio-models-for-powerful-voice-interactions-nxigikvvz) · DeepMind · 0 upvotes · 0 comments --- Tags: [#google](https://daily.dev/tags/google), [#google-gemini](https://daily.dev/tags/google-gemini), [#voice-ai](https://daily.dev/tags/voice-ai) [View this post on daily.dev](https://daily.dev/posts/introducing-gemini-3-8-live-and-3-8-live-extended-thinking-cicfsv9uc) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking","url":"https://daily.dev/posts/introducing-gemini-3-8-live-and-3-8-live-extended-thinking-cicfsv9uc","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-gemini-3-8-live-and-3-8-live-extended-thinking-cicfsv9uc"},"datePublished":"2026-09-30T20:06:22.437Z","dateModified":"2026-09-30T20:06:45.328Z","description":"Google announced two new Gemini audio models, Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, aimed at powering real-time voice agents and more natural...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/99bfbf3af344c6f654565b19d4779d2b?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/99bfbf3af344c6f654565b19d4779d2b?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"DeepMind","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"DeepMind","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/dm","url":"https://daily.dev/sources/dm"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/introducing-gemini-3-8-live-and-3-8-live-extended-thinking-cicfsv9uc","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"google,google-gemini,voice-ai","timeRequired":"PT4M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"DeepMind","item":"https://daily.dev/sources/dm"},{"@type":"ListItem","position":3,"name":"Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/introducing-gemini-3-8-live-and-3-8-live-extended-thinking-cicfsv9uc#faq","mainEntity":[{"@type":"Question","name":"What is Gemini 3.8 Live Extended Thinking and how does it perform on voice benchmarks?","acceptedAnswer":{"@type":"Answer","text":"Gemini 3.8 Live Extended Thinking is a Google voice model built for high-complexity, multi-step reasoning tasks in real-time conversation. It ranks first on Artificial Analysis' Speech to Speech Quality Index with a score of 82.6, scores 68.6% on τ-Voice and 35.1% on Sierra's τ-Voice-banking benchmark, and reaches 97.7% on Big Bench Audio. Developers evaluating voice agent models can track benchmark comparisons like these on daily.dev."}},{"@type":"Question","name":"How can I integrate Gemini Live API into a voice agent application?","acceptedAnswer":{"@type":"Answer","text":"The Gemini Live API can be integrated through developer platforms including Agora, Fishjam, LangChain, LiveKit, Pipecat, Vercel, and Vision Agents, which handle real-time media streaming infrastructure so developers can focus on the user experience. It's available in the Gemini API and Google AI Studio, with enterprise access in private preview via Gemini Enterprise. Developers building voice-driven apps follow API and platform integration news like this on daily.dev."}},{"@type":"Question","name":"How does Gemini 3.8 Live handle multiple languages and background tasks during a conversation?","acceptedAnswer":{"@type":"Answer","text":"Gemini 3.8 Live automatically detects and switches between 97 supported languages mid-conversation without interruption. It also executes tool calls and API requests in the background while continuing the dialogue, acknowledging user requests and keeping the conversation flowing while tasks complete asynchronously. Teams building multilingual voice agents can follow model capability updates like this on daily.dev."}}]} ```