Generative AI
Apr 15, 2026
Gemini 3.1 Flash TTS Launches with Enhanced AI Speech Control and Quality
Apr 15, 2026
AI Summary
The Gemini 3.1 Flash TTS model offers improved speech quality and control, allowing users to adjust vocal style and pacing through audio tags in over 70 languages. All generated audio includes SynthID watermarking to identify AI content and prevent misinformation.
- Gemini 3.1 Flash TTS is a new text-to-speech model that enhances expressiveness and quality of AI-generated speech.
- The model allows users to control vocal style, pace, and delivery using audio tags embedded in text input.
- It supports over 70 languages and features native multi-speaker dialogue.
- Gemini 3.1 Flash TTS achieved a high Elo score on the Artificial Analysis TTS leaderboard, indicating its quality and attractiveness for developers.
- Developers can utilize Google AI Studio to experiment with the model and fine-tune voice settings for various applications.
- All audio generated by the model is watermarked with SynthID to help identify AI-generated content and combat misinformation.
ai speechtext to speechgemini 3.1google productsexpressive ai