Fish Audio Drama 3: Benchmarks, Pricing & Examples
Fish Audio Drama 3 is a text-to-speech model from Fish Audio, released in October 2026.
Fish Audio's most emotive directed text-to-speech model. 35B MoE (~3B active), initialized from Qwen3.5-35B-A3B; 83 languages; stage directions in square brackets. Open weights under the Fish Audio Community License v1.0 (commercial free
Fish Audio Drama 3 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Quality Tracker
Fish Audio Drama 3 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Fri Nov 13 2026Try now
huggleGive your ideas
a voice.
Bring your next story, script, or creative project into your Huggle workspace.
Opens in Huggle
Fish Audio Drama 3 latency
Fish Audio Drama 3 time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Fish Audio Drama 3 license
Fish Audio Drama 3 is a proprietary model available under its provider's product and API terms, has 35.0B parameters.
- License
- Fish Audio Community License v1.0
- Hosted access
- Parameters
- 35.0B
Fish Audio Community License v1.0 — free for research and non-commercial use, and free for commercial use if you and your affiliates have less than US$500,000 in annual revenue; otherwise a separate commercial agreement is required.
Fish Audio Drama 3 resources
Official sources for Fish Audio Drama 3: provider documentation, official playground, paper or system card, official launch post, model weights.
FAQ
Common questions about Fish Audio Drama 3.