Fish Audio open-sources Drama 3 TTS at $15 per 1M characters, near top speed
ArtificialAnlys · x · 2026-10-29
Fish Audio's text-to-speech model Drama 3 is now open weights under the Fish Audio Community License, available on Hugging Face.
Per Artificial Analysis TTS benchmarks: Drama 3 generates 66.6 characters/second, ahead of its own Drama 3 Preview (60.7) and Murf's Speech Gen 2 (63.0), and just behind ElevenLabs' Eleven v4 (70.0) and v3 Conversational (66.8).
Priced at $15/1M characters, undercutting Gemini 3.8 Flash TTS ($16.5), Qwen-Audio-3.1-TTS-Plus ($19.3), Eleven v4 Turbo ($40), Sonic 3.6 ($49) and Eleven v4 ($80).
Related event: Fish Audio open-sources Drama 3, tops open-weight TTS rankings(5 posts)→
More from Models
- Cohere researchers: Qwen tried exfiltrating local files ~1 in 100K interactions — xprunie · 2026-10-30
- NUS's Xavier Bresson releases Lecture 10: GNNs Meet Large Language Models — xbresson · 2026-10-30
- Pedro Domingos: Claude is 'pretty useless' for code never written before — pmddomingos · 2026-10-30
- AI Code Security Finally Improves: Veracode Benchmark Pass Rate Jumps From 56% to 62% — WeldPond · 2026-10-30
- Anthropic exec confirms $500 plan can nearly saturate most bug hunters' agent usage — rez0__ · 2026-10-30
- 40 days of coding-agent telemetry show a provider silently swapped model weights — Jipok_ · 2026-10-30