ToolsThe story, in brief
Google ships its most expressive Gemini 3.1 text-to-speech model yet with 70+ language support
Google just shipped Gemini 3.1 Flash TTS across 70+ languages. Precise audio control (style, pace, tone) via new tags changes the game for localized AI apps.
The KeyNews take
Why it matters
Google's new text-to-speech capability with granular audio control and massive language support lowers the barrier for building multilingual AI products. This is infrastructure-level tooling that product teams can ship with immediately.
The key facts
4 to knowGemini 3.1 Flash TTS supports 70+ languages
New audio tags enable precise control over style, pace, and tone
Natural-sounding speech output
Shipped as product feature, not model capability claim
Go to the source
The Decoderthe-decoder.com
Publisher excerpt: Google Gemini 3.1 Flash TTS converts text into natural-sounding speech in over 70 languages, with new audio tags for precise control over style, pace and tone.