Google DeepMind releases Gemini 3.8 Flash TTS and Flash-Lite TTS speech generation models
Gemini 3.8 text-to-speech says hello
AI BriefingGoogle DeepMind releases two text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, supporting voice design from scratch through natural-language prompts, voice cloning from 30-second samples, line-by-line performance direction, long-form audio generation, and two-speaker scene arrangement across more than 100 languages.
Another 10 sources reported this
- Google Releases Gemini 3.8 Flash TTS and Other UpdatesGoogle AI · September 26
- Google releases Gemini 3.8 TTS models; Simon Willison builds a voice PlaygroundSimon Willison's blog · September 24
- Google Releases Gemini 3.8 Flash TTS and Flash-Lite TTS, Supporting Prompt-Based Voice DesignMarkTechPost · September 24
- Google releases Gemini 3.8 Flash TTS and Flash-Lite TTS, enabling users to design AI voices from scratch using text descriptionsThe Decoder: AI News · September 24
- Google releases the Gemini 3.8 Flash TTS and Flash-Lite TTS speech generation modelsHacker News: Popular AI Post · September 24
- Google releases Gemini 3.8 Flash TTS and Flash-Lite TTS text-to-speech modelsIT Home · Artificial Intelligence · September 24
- Google releases the Gemini 3.8 Flash and Flash-Lite TTS speech modelsLogan Kilpatrick · September 24
- Google releases Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTSArtificial Analysis · September 23
- Google releases the Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS speech modelsGoogle AI · September 23
- Google DeepMind releases Gemini 3.8 Flash TTS and Flash-Lite TTS text-to-speech modelsGoogle DeepMind · September 23
Source: Google DeepMind: Blog · deepmind.google
Event follow-up1
View all event coverage- Google DeepMind releases Gemini 3.8 Flash TTS and Flash-Lite TTS speech generation modelsGoogle DeepMind: Blog · September 23