Gemini 3.1 Flash TTS adds inline audio tags across 70+ languages
- Source
- x.com
- Date
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 ↓
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
Context
Gemini 3.1 Flash TTS adds delivery instructions inside the text being converted to speech. These audio tags let a script change tone, pace or expression at a particular passage, giving creators control over how words are spoken as well as which words appear. Google AI introduced the capability in its April 15, 2026 launch explanation.
The accompanying announcement lists support for more than 70 languages but identifies 24 as high-quality evaluated languages. That separates broad language availability from the narrower set covered by that quality designation.
- postGoogle's week: EmbeddingGemma 2, Nano Banana 2.1, Gemini business agent
postGoogle opens SynthID watermark checks to everyone, with partner coverage
postGemma 4 orchestrates a plant DNA model to find crop mutations in minutes
articleGoogle's Project CC gives a family agent its own identity and sandbox
Checking sign-in…
Loading comments…