模型与实验室 4.0 · 优秀 2026-06-07 · X

Gemini 3.1 Flash TTS:表现力最强控制粒度最细的语音合成模型

今天我们发布了 Gemini 3.1 Flash TTS迄今为止表现力最强控制粒度最细的文本转语音模型 本次发布包含音频标签(Audio Tags)功能!音频标签是一种无缝的方式,用嵌入在文本中的自然语言命令来引导语音风格节奏和表达方式想要不同的语速或语调?给音频加上标签,AI 语音输出就会按你的指令来!...

打开原文回到归档

Gemini 3.1 Flash TTS:表现力最强控制粒度最细的语音合成模型

English

| id | author | bio | text | likes | retweets | url | has_media | media_urls | card | quoted_tweet | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | 2044447560384102592 | GoogleAI | Making AI helpful for everyone. Show thinking ↓ | Today we launched Gemini 3.1 Flash TTS, our most expressive and controllable text-to-speech model yet.

This launch [excitement] includes audio tags! 🗣🏷 Audio tags [explanatory] are a seamless way to guide vocal style, pace, and delivery using natural language commands embedded directly in your text. Want a different tempo or tone? [amazement] Just tag the audio to steer the AI-speech output!

The model supports 70+ languages (24 of which are high-quality evaluated languages, including: Japanese, Hindi, and Arabic). Watch the audio tags in action in the demo below ↓ | 2294 | 310 | https://x.com/GoogleAI/status/2044447560384102592 | true | https://video.twimg.com/amplify_video/2044447449708990464/vid/avc1/424x270/9J7JcG155K5NJApE.mp4?tag=21 | | | | 2044447638511383024 | GoogleAI | Making AI helpful for everyone. Show thinking ↓ | Gemini 3.1 Flash TTS is rolling out in Google Vids and is available today in preview via the Gemini API and in @GoogleAIStudio.

Whether you’re creating a pitch deck or recording a passion project, transform your scripts into studio-quality narration: https://t.co/MG2YIQwKb6 | 106 | 14 | https://x.com/GoogleAI/status/2044447638511383024 | false | | [object Object] | | | 2044924653592780939 | yonggan8964 | UN难民! 用生命诠释捍卫自由!如果自由在远方我愿意死在路上! 有缺点的战士总归是战士,再完美的苍蝇还是苍蝇! 有些路你必须独自走! 没有家人,没有朋友,没有伴侣。 只有你和上帝。https://t.co/Dy6jYpmtzd | I am a paid subscriber. I frequently use your AI to discuss strategies for countering the Chinese Communist Party's transnational repression against me in the United States. However, my Gemini access has been blocked: the photos and videos I send are invisible to your AI, and the voice functionality has ceased working. I do not know what has happened. Was my conversation censored by CCP agents, or is there a technical bug on your end? I demand an explanation! My account email is zhoujunfree614@gmail.com. Thank you. | 0 | 0 | https://x.com/yonggan8964/status/2044924653592780939 | false | | | | | 2044573336328696294 | mtzjp | AI鬱にならんよう体を鍛えようと思います。サバイバル術を子供に教えないとな。2児の父。ベースはXR、Web等などのフロントエンド、3DCG等々。 | @GoogleAI @GoogleAIStudio なんか最近TTS祭りなの? | 0 | 0 | https://x.com/mtzjp/status/2044573336328696294 | false | | | | | 2044549724603056194 | travasites | 🥇 @Nextjs @Supabase @Vercel

Building Online Stores That Makes Millions💸💰While You Sleep. | @GoogleAI @GoogleAIStudio Nice to see TTS getting the “Flash” treatment low latency matters for real time narration. Curious how the voice quality compares to ElevenLabs or Azure TTS, and whether the API supports streaming or SSML. Definitely giving this a try in AI Studio. | 0 | 0 | https://x.com/travasites/status/2044549724603056194 | false | | | | | 2044469286765256749 | PromptSlinger | I write one prompt. Whole galaxies fall out. Bridging the gap between prompts and real work. AI Educator. Absurdist. Builder. Stick around, I'll teach you. | @GoogleAI @GoogleAIStudio wait so the pitch deck thing, does it handle different speaker voices in the same script? or is it one narrator per video | 0 | 0 | https://x.com/PromptSlinger/status/2044469286765256749 | false | | | | | 2044455041033961545 | _Leon_Lapaix | | @GoogleAI @GoogleAIStudio Is it planned in the short or medium term to integrate it into PlayBook for TTS audio reading of books? https://t.co/O8Zt5N9w2d | 0 | 0 | https://x.com/_Leon_Lapaix/status/2044455041033961545 | true | https://pbs.twimg.com/media/HF9dBrtXkAEKQJe.jpg | | | | 2044451115815653450 | dan_in_robots | Embajador entre el mundo humano y el robótico. | @GoogleAI @GoogleAIStudio Audio tags for steering speech output, exactly the practical control developers need. Already testing in AI Studio. | 1 | 0 | https://x.com/dan_in_robots/status/2044451115815653450 | false | | | | | 2044449196468817993 | Madhav_2077 | building with AI before it builds without us | automation, agents & stuff that actually works | 21 y/o Ai guy. | @GoogleAI @GoogleAIStudio Can we get flash lite preview? | 0 | 0 | https://x.com/Madhav_2077/status/2044449196468817993 | false | | | |

中文

[中文翻译将在实际实现中完成]

*本内容由 AI Field Notes 内容抓取器于 2026-06-10 获取*