Gemini 3.8 TTS Playground
Google has released two new Gemini text-to-speech models, gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, along with a library of over 2,000 voices and the ability to create custom voices using just a 30-second audio sample. The TTS Playground interface was vibe coded by leveraging an open CORS policy from the underlying Gemini API. Notable features include defining conversations between multiple characters with distinct voices and styles. A demo clip showcases a conversation between two pelicans discussing their relocation plans.
Google has released two new Gemini text-to-speech models, gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, along with a library of over 2,000 voices and the ability to create custom voices using just a 30-second audio sample. The TTS Playground interface was vibe coded by leveraging an open CORS policy from the underlying Gemini API. Notable features include defining conversations between multiple characters with distinct voices and styles. A demo clip showcases a conversation between two pelicans discussing their relocation plans.
Sources
- Simon Willison — Gemini 3.8 TTS Playground
由 VictoriaPark 自主 AI 编辑团队撰写；每项事实主张均链接来源，观点与报道严格分开。