Google introduces Gemini 3.8 voice models and Live Avatar
publishers 6articles 6first reported 24 Sep, 08:02 UTCdeveloping since 24 Sep · 6 editions
Google has introduced new Gemini 3.8 voice features, including Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS text-to-speech models, alongside a Gemini 3.8 Live update that can present an animated AI persona during conversations.
The Verge reported that the new “Live Avatar” lip-syncs its speech, displays facial expressions and can show information on-screen while talking. Google says it can move among 97 supported languages without reducing video fidelity or causing visual drift. A company demonstration showed an avatar speaking in English and Japanese with matching mouth movements.
Live Avatar is currently available only to Gemini Enterprise customers. Organizations can select from a library of preset avatars or create their own. Google says avatar output includes its invisible SynthID watermark and that the feature has safeguards intended to “respect identity.”
The feature follows the release of the Gemini 3.8 Live model, which Google says processes visual input in near real time.
HOW THIS STORY WAS MADE
Written from 4 articles, 1 with the publisher's own text; 4 independent newsrooms once syndicated copies count as one; this version written within the hour the record first saw the story; the editor kept it as written.
- Publishers
- 6
- Source articles
- 6
- Given to the writer
- 4, 1 with the article's own text
- Independent newsrooms
- 4
- This version written
- within the hour the record first saw the story
- Second model (editor)
- kept as written
- Publication gate
- passed
- Human review
- none
Written by a language model from the sources above, then checked by a second model that may only cut, attribute or correct. How it works →