Gemini 3.1 Flash TTS: Controllable Speech with Audio Tags
Melvin Vivas · X post · 2026-04-16 · Open on X
Topics: Industry Trends & Job Market, AI Dev Tools & Productivity · Level: beginner
Summary
The creator shares the release of Gemini 3.1 Flash TTS, which Google calls its most controllable text-to-speech model. New Audio Tags let you set vocal style, delivery and pace with text commands.
Key points
- Gemini 3.1 Flash TTS is Google's newest text-to-speech model.
- It is described as Google's most controllable TTS model yet.
- Audio Tags are text commands placed in the input to control vocal style, delivery and pace.
Resources mentioned
- Gemini 3.1 Flash TTS · tool · blog.google · check price · open in a browser to verify
Google's text-to-speech model with Audio Tags for controlling style, delivery and pace.
Try this
- Use Audio Tags in Gemini 3.1 Flash TTS to produce narration in different styles and paces.
More in Industry Trends & Job Market
- SpaceXAI and Cursor partner on coding AI
- Seedance 2.0 Video Model Now Available Inside HeyGen (Demo Clip)
- Claude Opus 4.7 Release: More Rigor on Long-Running Tasks
- Rumored Anthropic App Builder vs bolt.new, Lovable and v0
- GLM-5.1 Reportedly Beats Claude Opus 4.6 on Cybersecurity
- Open-Source GLM-5.1 Beats GPT-5.4 on SWE-Bench Pro