Google DeepMind 发布 Gemini 3.1 Flash TTS 文本转语音模型
Gemini 3.1 Flash TTS: New text-to-speech AI model
Google DeepMind 推出 Gemini 3.1 Flash TTS，通过 audio tags 精细控制语音风格、节奏和表达，并支持 70 多种语言及原生多说话人对话。该模型在 Artificial Analysis TTS 排行榜获得 1,211 Elo 分，正逐步上线 Google AI Studio、Vertex AI 和 Google Vids；生成的音频均带有 SynthID 水印。
推荐理由
精选AI 评分 78
原文提供语音质量基准、语言覆盖和音频标签能力，可用于评估模型在多语言语音应用中的可控性与成本平衡。
主题
正文
当前显示原文，中文全文译文尚未就绪。
Apr 15, 2026
Our newest audio model introduces granular audio tags that give you precise control to direct AI speech for expressive audio generation.
Principal Research Engineer on behalf of the Gemini team
Your browser does not support the audio element.
Gemini 3.1 Flash TTS is here, giving you improved AI speech quality and control. You can now use audio tags to adjust vocal style and pacing in over 70 languages. Test it out in Google AI Studio, Vertex AI, and Google Vids, and know that all audio is watermarked with SynthID to prevent misinformation.
Gemini 3.1 Flash TTS is a new AI that makes computer speech sound more real. It lets people change how the AI talks by using special commands in the text. This AI can speak in over 70 languages and adds a hidden watermark to the audio. This helps people know it's AI-generated and not a real person.
Today, we’re introducing Gemini 3.1 Flash TTS, the latest text-to-speech model that delivers improved controllability, expressivity and quality — empowering developers, enterprises and everyday users to build the next generation of AI-speech applications.
Starting today, 3.1 Flash TTS is rolling out:
We’ve improved the overall speech quality of Gemini 3.1 Flash TTS, making it our most natural and expressive model to date. On the Artificial Analysis TTS leaderboard , a benchmark that captures thousands of blind human preferences, 3.1 Flash TTS achieved an impressive Elo score of 1,211.
Artificial Analysis has also positioned Gemini 3.1 Flash TTS within its “ most attractive quadrant ” for its ideal blend of high-quality speech generation and low cost. The model stands out further with native multi-speaker dialogue, support for 70+ languages, and granular creative control via natural language.
3.1 Flash TTS also introduces audio tags — an intuitive way to control vocal style, pace and delivery. By embedding natural language commands directly into the text input, you can steer AI-speech output with improved levels of granularity.
You can start experimenting with these audio tags along with other updates to the developer experience in Google AI Studio with configurable controls that place the developer in the “director’s chair”:
With these new configurations, developers can enhance precision for specific scenarios, creating memorable characters and immersive audio experiences.
Gemini 3.1 Flash TTS delivers high-fidelity speech and more precise control across more than 70 languages. These core optimizations bring advanced style, pacing and accent control to major markets — helping developers create localized, expressive speech experiences for users at global scale.
Early developer and enterprise testers are already seeing the impact of 3.1 Flash TTS, highlighting its impressive controllability and expressivity. They’ve told us how audio tags provide a new level of creative precision, transforming simple text into a high-fidelity vocal performance.
All audio generated by Gemini 3.1 Flash TTS is watermarked with SynthID. This imperceptible watermark is interwoven directly into the audio output, allowing the reliable detection of AI-generated content to help prevent misinformation. For more information on our approach to safety and responsibility, you can review the model card .
Done. Just one step more.
Check your inbox to confirm your subscription.