Gemini 3.8 text-to-speech says hello
Google DeepMind introduced Gemini 3.8 Flash and Flash-Lite text-to-speech models for expressive audio.
Google DeepMind announced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS for Google AI Studio, the Gemini API, Gemini Enterprise, Gemini Notebook, and Google Vids. The models add natural-language voice design, more than 2,000 production voices, line-level performance control, and replication from a 30-second consented sample, with SynthID watermarking and C2PA credentials. Flash TTS placed first on Hume AI’s Voice Design Benchmark at 71.4 and first on the Overall Quality Index, ahead of Flash-Lite, with support for over 100 languages.
- DeepMind announced Gemini 3.8 Flash TTS and Flash-Lite TTS.
- Voice design, 2,000-plus voices, and 30-second replication supported.
- Safeguards include consent checks, SynthID, and C2PA credentials.
- Flash TTS leads Hume’s Voice Design Benchmark with a 71.4 score.
- Vendors
- Organizations
- Google DeepMindGoogle
From the original article
5 min read at deepmind.google
Gemini 3. 8 Flash TTS and Gemini 3. 8 Flash-Lite TTS are our most expressive audio generation models yet.
deepmind.google
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.