modelsApr 15
Gemini 3.1 Flash TTS: the next generation of expressive AI speech
Google DeepMind released Gemini 3.1 Flash TTS, an updated audio model for expressive speech generation. The model introduces granular audio tags for precise control over AI-generated speech. This allows for more nuanced and customizable audio output. You can use it to create more realistic and varied speech synthesis.
Key takeaways
- Gemini 3.1 Flash TTS supports granular audio tags for expressive speech.
- Enables precise control over AI-generated speech characteristics.
- Improves customization and realism in audio output.