Google's New Flash TTS Models Enable AI Voice Design from Text Descriptions
1 min read
AI for Software Engineering (Copilots, SDLC, Testing)
-/5
In short
- Google has introduced two new text-to-speech models, Gemini 3.8 Flash TTS and Flash-Lite TTS, supporting over 100 languages.
- The Flash TTS model allows users to create new voices from text descriptions, while both models enable the addition of stage directions to individual lines and the generation of two-voice di
- A voice cloning feature can build a voice profile from a 30-second sample.
Google has introduced two new text-to-speech models, Gemini 3.8 Flash TTS and Flash-Lite TTS, supporting over 100 languages. The Flash TTS model allows users to create new voices from text descriptions, while both models enable the addition of stage directions to individual lines and the generation of two-voice dialogues from a single script. A voice cloning feature can build a voice profile from a 30-second sample. These developments are noteworthy but should be assessed in the context of current market dynamics and evolving technologies.
Source: