DigestAI news desk

Cut through the AI noise.

Enterprise & Industryupdated 2 min read

Gemini introduces 3.8 Live with Live Avatar

Gemini today announced Gemini 3.8 Live with Live Avatar, adding near real‑time video generation and lip‑syncing to its live dialogue models.

2 sources primary source

Key points

  • Gemini 3.8 Live with Live Avatar adds near real‑time video generation and lip‑syncing to Gemini Enterprise
  • Supports 97 languages with native multilingual speech‑to‑speech
  • Custom avatars can be created from a reference image, available only through enterprise allowlisting

The new feature lets enterprises create visual personas that listen, see, and speak, supporting 97 languages with native multilingual speech‑to‑speech. It also offers a library of preset avatars and a custom avatar tool that can generate a fully animated character from a reference image, though the custom option is only available through enterprise allowlisting.

Gemini 3.8 Live with Live Avatar is available in Gemini Enterprise and is built with safeguards such as SynthID watermarks to keep AI‑generated content transparent.

Model page: Gemini 3.8 Live →

Full story from Google DeepMind · by Shuo-yiin Chang primary sourceOpen source ↗

Introducing Gemini 3.8 Live with Live Avatar

Google DeepMind · 24 September 2026

Loading the full article…

This text was published by Google DeepMind and written by Shuo-yiin Chang. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Coverage and discussion

2sources
Topics · follow one to build your own front page
Gemini 3.8 Live with Live Avatar

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Enterprise & Industry

All →

Related stories