Report
Google makes custom voices self-serve in Gemini 3.8 TTS
The New Stack reports that developers can design a voice from a text prompt or replicate one from a short clip.
TLDR
The New Stack reports that Google's Gemini 3.8 TTS lets developers create a voice from a text prompt or replicate one from a short clip, then reuse it by ID through the Gemini API. The outlet contrasts that self-serve option with OpenAI's custom-voice process, which it says requires contacting sales.
Combined views
718
1 Source, first seen ago