DeepMind Unveils Gemini 3.1 Flash TTS with Enhanced AI Speech Capabilities
2 sources·2 updates
DeepMind has launched the Gemini 3.1 Flash TTS, a new AI speech model that significantly improves expressiveness and control over vocal output. The model supports over 70 languages and introduces audio tags that allow developers to customize speech characteristics, enhancing creative precision in applications. Additionally, all generated audio is watermarked with SynthID to help identify AI-generated content and combat misinformation.
Key Points
Gemini 3.1 Flash TTS achieved an Elo score of 1,211 on the Artificial Analysis TTS leaderboard.
Timeline
Get personalized news summaries delivered to your feed
Try Trace Free