Vibeleaderboard
← All Intel
Intel / post

Fish Audio previews Drama 3 directable speech model

Source
x.com
Date
Fish Audio@FishAudio

Drama 3 doesn't just read lines. It brings the drama. Direct the performance in plain language: tone, emotion, pacing, character. It can even shift emotion mid-line, no retake needed. Try the preview now in the API with 'drama-3-preview'.

Why it matters

Fish Audio's drama-3-preview model takes plain-language direction for tone, emotion, pacing and character, and can change emotion mid-line, so voice- builders can test expressive control through the API without retakes.

Terms in this piece · Glossary
  • AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
More from Fish Audio
Recommended reads
Comments

Checking sign-in…

Loading comments…