Updated · The Keyword | Google Product and Technology News · Sep 23
Gemini Launches 2 New 3.8 TTS Models With 100-Language Voice Generation
Updated
Updated · The Keyword | Google Product and Technology News · Sep 23
Gemini Launches 2 New 3.8 TTS Models With 100-Language Voice Generation
3 articles · Updated · The Keyword | Google Product and Technology News · Sep 23
Summary
Gemini rolled out 3.8 Flash TTS and 3.8 Flash-Lite TTS on Wednesday, adding new text-to-speech models aimed at creators, developers and enterprises.
3.8 Flash TTS focuses on custom voice creation and line-by-line performance control, while Flash-Lite targets lower-cost, high-volume dubbing and voice-agent use.
The launch adds voice generation across 100-plus languages and dialects, 2,000-plus production-ready voices, and voice replication from a 30-second sample with consent verification.
Gemini said the models ranked No. 1 and No. 2 on Hume AI’s Overall Quality Index, with Flash TTS also taking the top Voice Design Benchmark score at 71.4.
Starting today, the models are available in the Gemini API and Google AI Studio, with Flash TTS also rolling into Gemini Notebook and Flash-Lite into Google Vids.