--- title: Introducing Gemini 3.8 Live with Live Avatar | daily.dev description: Google announced Gemini 3.8 Live with Live Avatar, a feature adding near real-time video generation with precise lip-syncing and natural expressions to its... canonical: https://daily.dev/posts/introducing-gemini-3-8-live-with-live-avatar-icafbad0i twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Introducing Gemini 3.8 Live with Live Avatar | daily.dev og:description: Google announced Gemini 3.8 Live with Live Avatar, a feature adding near real-time video generation with precise lip-syncing and natural expressions to its... og:url: https://daily.dev/posts/introducing-gemini-3-8-live-with-live-avatar-icafbad0i og:image: https://api.daily.dev/og/posts/IcAfbad0i.png og:image:alt: Introducing Gemini 3.8 Live with Live Avatar 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 with Live Avatar **[DeepMind](https://daily.dev/sources/dm)** · 3 min read · 0 upvotes · 0 comments ## Summary Google announced Gemini 3.8 Live with Live Avatar, a feature adding near real-time video generation with precise lip-syncing and natural expressions to its live conversational AI model. It supports asynchronous tool calling during dialogue, works across 97 languages without visual drift, and allows enterprises to customize avatars from a reference image. Output is watermarked with SynthID. The feature is available now in Gemini Enterprise. ## 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 with Live Avatar and what does it add to Gemini's live conversational model? Gemini 3.8 Live with Live Avatar adds near real-time video generation paired with speech to Gemini's native live dialogue models, creating a dynamic visual persona with precise lip-syncing, natural expressions, and fluid turn-taking. It supports asynchronous tool calling during active conversation and native multilingual speech-to-speech sync across 97 languages. It launched in Gemini Enterprise. _Developers building enterprise conversational agents can track Gemini's live avatar rollout on daily.dev._ ### How many languages does Gemini's Live Avatar feature support without losing video quality? It supports 97 languages, dynamically adapting lip-sync and facial expressions during speech-to-speech transitions without degrading video fidelity or introducing visual drift. This multilingual synchronization is built into the Live Avatar feature released alongside Gemini 3.8 Live, aimed at enterprises deploying conversational agents across global markets. _Teams evaluating multilingual AI agents can follow updates like this on daily.dev._ ### How does Google ensure AI-generated avatar video and audio from Gemini Live Avatar can be identified as synthetic? All output from Gemini Live Avatar is watermarked with SynthID, an imperceptible watermark woven directly into both the audio and video streams. This is designed to keep AI-generated content detectable and help reduce misinformation and misattribution risks tied to synthetic avatars used in enterprise conversational deployments. _Developers weighing AI content provenance concerns can follow tools like SynthID on daily.dev._ ## Similar posts on daily.dev - [Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking](https://daily.dev/posts/introducing-gemini-3-8-live-and-3-8-live-extended-thinking-cicfsv9uc) · DeepMind · 0 upvotes · 0 comments - [Google launches Gemini Omni Flash, a conversational video-generation model with avatar mode held back](https://daily.dev/posts/google-launches-gemini-omni-flash-a-conversational-video-generation-model-with-avatar-mode-held-bac-inyx9rzgc) · The Next Web · 0 upvotes · 0 comments - [Gemini Live API available on Vertex AI](https://daily.dev/posts/gemini-live-api-available-on-vertex-ai-pwpyu7zkz) · Google Cloud · 1 upvotes · 0 comments --- Tags: [#gcp](https://daily.dev/tags/gcp), [#google-gemini](https://daily.dev/tags/google-gemini), [#conversational-ai](https://daily.dev/tags/conversational-ai) [View this post on daily.dev](https://daily.dev/posts/introducing-gemini-3-8-live-with-live-avatar-icafbad0i) ```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 with Live Avatar","url":"https://daily.dev/posts/introducing-gemini-3-8-live-with-live-avatar-icafbad0i","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-gemini-3-8-live-with-live-avatar-icafbad0i"},"datePublished":"2026-09-30T20:06:22.554Z","dateModified":"2026-09-30T20:07:23.569Z","description":"Google announced Gemini 3.8 Live with Live Avatar, a feature adding near real-time video generation with precise lip-syncing and natural expressions to its...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0d7d7b1c53e2222ac1c7e99ecf2e11ee?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/0d7d7b1c53e2222ac1c7e99ecf2e11ee?_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-with-live-avatar-icafbad0i","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"gcp,google-gemini,conversational-ai","timeRequired":"PT3M"} {"@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 with Live Avatar"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/introducing-gemini-3-8-live-with-live-avatar-icafbad0i#faq","mainEntity":[{"@type":"Question","name":"What is Gemini 3.8 Live with Live Avatar and what does it add to Gemini's live conversational model?","acceptedAnswer":{"@type":"Answer","text":"Gemini 3.8 Live with Live Avatar adds near real-time video generation paired with speech to Gemini's native live dialogue models, creating a dynamic visual persona with precise lip-syncing, natural expressions, and fluid turn-taking. It supports asynchronous tool calling during active conversation and native multilingual speech-to-speech sync across 97 languages. It launched in Gemini Enterprise. Developers building enterprise conversational agents can track Gemini's live avatar rollout on daily.dev."}},{"@type":"Question","name":"How many languages does Gemini's Live Avatar feature support without losing video quality?","acceptedAnswer":{"@type":"Answer","text":"It supports 97 languages, dynamically adapting lip-sync and facial expressions during speech-to-speech transitions without degrading video fidelity or introducing visual drift. This multilingual synchronization is built into the Live Avatar feature released alongside Gemini 3.8 Live, aimed at enterprises deploying conversational agents across global markets. Teams evaluating multilingual AI agents can follow updates like this on daily.dev."}},{"@type":"Question","name":"How does Google ensure AI-generated avatar video and audio from Gemini Live Avatar can be identified as synthetic?","acceptedAnswer":{"@type":"Answer","text":"All output from Gemini Live Avatar is watermarked with SynthID, an imperceptible watermark woven directly into both the audio and video streams. This is designed to keep AI-generated content detectable and help reduce misinformation and misattribution risks tied to synthetic avatars used in enterprise conversational deployments. Developers weighing AI content provenance concerns can follow tools like SynthID on daily.dev."}}]} ```