Fish Audio launches Drama 3 preview, billing it as the most controllable TTS model ever
bdsqlsz · x · 2026-09-24
Fish Audio has released Drama 3 (preview), which it calls the most controllable TTS model ever. Users describe tone, pacing, and character in plain language instead of audio tags, can shift voice mid-sentence, generate multi-character scenes, or fix a single word without regenerating the whole clip. Commenters can request an API key to try it.
More from Multimodal
- MiniMax H3 hits 100 days open-source: 1,472 derivative models, 148M+ downloads — linoy_tsaban · 2026-11-11
- MiniMax H3-Image explodes an espresso machine photo into 15 labeled parts — Charlietest123 · 2026-11-11
- Indie dev built a tool that clips best moments from 4-hour streams in 30 minutes — kissaadams · 2026-11-11
- Non-Blender user makes a video in 30 minutes with Claude and Seedance — FinanceYF5 · 2026-11-11
- Whimsical Woodland: A Watercolor AI Art Prompt Template for Dreamy Forest Scenes — LudovicCreator · 2026-11-11
- Clean point clouds: Tersus GNSS MVP S1 scans turned into high-quality splats in LichtFeld Studio — janusch_patas · 2026-11-11