Gemini 3.8 TTS Playground
Google released two new Gemini 3.8 text-to-speech models with 2,000+ voices and custom voice cloning.
“just a 30-second audio sample of your voice or a voice you have the rights to use”
Google launched gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, offering over 2,000 voices, 30-second custom voice cloning, and easy multi-speaker conversation generation via an open-CORS API. It matters because it lowers the cost and effort of high-quality, controllable synthetic speech, with ~78 seconds of multi-voice audio generated in ~20 seconds for under 3 cents.