Gemini 3.1 Flash TTS is our most controllable text-to-speech model yet.
With new Audio Tags, you can easily direct vocal style, delivery, and pace through text commands. π§΅
VIDEO
π΅ More natural sounding speech
π΅ Support for 70+ languages like Hindi, Japanese, and German
π΅ SynthID watermarking on all outputs
π΅ Support for 70+ languages like Hindi, Japanese, and German
π΅ SynthID watermarking on all outputs

Hereβs where to find it:
Developers: Preview via Gemini API and @GoogleAIStudio
Enterprise: Rolling out in preview on Vertex AI
Everyone: Rolling out to @Google Vids
Find out more β goo.gle/3Orfb7I
Developers: Preview via Gemini API and @GoogleAIStudio
Enterprise: Rolling out in preview on Vertex AI
Everyone: Rolling out to @Google Vids
Find out more β goo.gle/3Orfb7I
Generated by Thread Navigator
Press β + S to quick-export
