Google ships Gemini 3.8 Live voice models and Gemini 3.8 Flash TTS with voice design and cloning
Confirmed
Status
- Claim
Confirmed
- Our reporting
- High confidence
- Importance
- 2 of 5
- Last verified
- 30 September 2026
Your AI and this story
- GPT-6 Astra138 days after its cutoff
- Claude Opus 5.577 days after its cutoff
- Gemini 4 Hydrogen168 days after its cutoff
- Grok 4.7107 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 77 days before it.
Key facts
- 2026-09-15: gemini-3.8-live and gemini-3.8-live-extended-thinking GA (audio-to-audio, real-time)
- 2026-09-22: gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts GA
- New /v1beta/voices endpoint, voice design, voice replication and an Extended Voice Library
- Earlier: gemini-3.5-transcribe and gemini-3.5-transcribe-live GA on 2026-08-26; Lyria 3.5 music model GA on 2026-09-03
- Sept 24, 2026: Gemini 3.8 Live with Live Avatar generally available in Gemini Enterprise: near-real-time talking avatar (24 FPS video, 24 kHz audio, sub-second latency), lip-sync in 97 languages, asynchronous background tool calls, SynthID watermarking; US and EU endpoints; custom avatars need allowlisting
- Google (Sept 15): Gemini 3.8 Live Extended Thinking ranks #1 on Artificial Analysis’ Speech-to-Speech Quality Index (82.6), scores 68.6% on a voice banking agent benchmark and 97.7% on Big Bench Audio; 3.8 Live handles near-real-time visual input, switches among 97 languages mid-conversation and runs tools in the background while talking
- Rolled out the same day in the Gemini app (Daily Brief, inbox), Google Workspace (Docs Live, Gmail Live, Keep Live) and Search Live; partners named: Salesforce, Genspark, Lumeris; output carries SynthID audio watermarks
What happened
Following Gemini 3.8 Flash, Google rolled the 3.8 generation into its real-time voice (Live) and text-to-speech models, adding APIs to design and replicate voices.
Why it matters
Completes a full voice stack (transcription, reasoning, real-time dialogue, speech synthesis, cloning) on one API; voice cloning also raises misuse concerns.
Sources
12 sources from 6 sites. Numbers match the chips in the text.
12 sources: 10 primary, 1 press, 1 reaction
Primary
- Google: Gemini 3.8 Live with Live Avatarblog.google, official
- Google Cloud: Gemini 3.8 Live with Live Avatar is now generally availablecloud.google.com, official
- Gemini API release notesai.google.dev, docs
- Gemini API models overviewai.google.dev, docs
- Google: Gemini 3.5 Transcribeblog.google, official
- Google DeepMind: Gemini 3.8 text-to-speech says hellodeepmind.google, official
- Google DeepMind: Introducing Gemini 3.8 Live with Live Avatardeepmind.google, official
- Google: Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking (Sept 15)blog.google, official
- Google DeepMind: Introducing Gemini 3.8 Live and 3.8 Live Extended Thinkingdeepmind.google, official
- Google blog: Gemini 3.8 text-to-speech says helloblog.google, official
Press
- The Verge: Gemini Live Avatar gives the AI a facetheverge.com, press
Reactions
- Simon Willison: Gemini 3.8 TTS Playgroundsimonwillison.net, discussion
Changes
- Added Google’s Sept 15 Gemini 3.8 Live launch post and its benchmark/availability details
- Added DeepMind blog posts on 3.8 TTS and Live Avatar, The Verge, and Simon Willison’s playground
- Added the Sept 24 GA of Live Avatar in Gemini Enterprise
- Linked related voice entries (Gemini 3.5 Live Translate, GPT-Live)
- Filed
