{"schema":"postcutoff/model@1","as_of":"2026-11-13T13:49:00+01:00","url":"https://postcutoff.com/m/fish-audio-s2/","md":"https://postcutoff.com/m/fish-audio-s2/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"fish-audio-s2","name":"Fish Audio S2 Pro / S2.1 Pro","org":"Fish Audio","family":"Fish Audio S2","released":"2026-03-09","status":"current","type":"audio/speech","modality_in":["text","audio"],"modality_out":["audio"],"open_weights":true,"model_license":"Fish Audio Research License (S2 Pro weights; non-commercial, commercial license on request)","context_window":null,"max_output":null,"knowledge_cutoff":null,"pricing":{"per_1m_utf8_bytes":15,"unit":"USD per 1M UTF-8 bytes (s1, s2-pro, s2.1-pro); s2.1-pro-free $0 under fair use through 2026-11-30; ASR transcribe-1 $0.36/hr","source":"https://docs.fish.audio/developer-guide/models-pricing/pricing-and-rate-limits"},"price_line":"$15 per 1M UTF-8 bytes","access":[{"provider":"Fish Audio API","model_id":"s2.1-pro","endpoint":"https://api.fish.audio/v1/tts (model passed in `model` header)","docs":"https://docs.fish.audio/developer-guide/getting-started/changelog"},{"provider":"Fish Audio API (free tier)","model_id":"s2.1-pro-free","endpoint":"https://api.fish.audio/v1/tts"},{"provider":"Fish Audio API","model_id":"s2-pro"},{"provider":"Hugging Face","model_id":"fishaudio/s2-pro","url":"https://huggingface.co/fishaudio/s2-pro"},{"provider":"OpenRouter","url":"https://openrouter.ai/fish-audio/s2.1-pro"},{"provider":"GitHub","url":"https://github.com/fishaudio/fish-speech"}],"capabilities":[{"name":"Inline natural-language emotion/paralinguistic tags","detail":"Free-form bracket cues like [whisper], [laugh], [emphasis]; multi-speaker dialogue in one pass; 80+ languages from 10M+ hours of training audio.","first":false,"discovered":"launch","source":"https://fish.audio/blog/fish-audio-open-sources-s2/"},{"name":"Open model with production inference stack","detail":"Dual-AR (4B slow + 400M fast) on a Qwen3-4B backbone released with fine-tuning code and SGLang serving; RTF 0.195, ~100 ms TTFA; Seed-TTS Eval WER 0.54% zh / 0.99% en.","first":false,"discovered":"launch","source":"https://arxiv.org/abs/2603.08823"},{"name":"Free production API (S2.1 Pro)","detail":"S2.1 Pro (closed, 2026-06-23) offered free under fair use with ~90 ms TTFA, 83 languages; 61% win rate vs S2 Pro.","first":false,"discovered":"later","source":"https://fish.audio/blog/s2-1-pro-free-api/"}],"entry":"2026-03-09-fish-audio-s2-open-source","notes":"S2 Pro held #1 open-weights on Artificial Analysis until Breeze TTS 2 (Aug 2026); now #2 open (~1119 Elo). S2.1 Pro weights are NOT open. OpenRouter lists S2.1 Pro release as 2026-07-29 (API availability there). Predecessor OpenAudio S1 (`s1`) is deprecated and retires 2026-12-31 (requests then served and billed as s2.1-pro). Successor: Drama 3 (2026-10-13, see fish-audio-drama-3); on Artificial Analysis S2 Pro is now the #3 open-weights model (Elo 1118, read 2026-10-13). The pricing page no longer shows an end date for s2.1-pro-free (read 2026-10-13).","verified":"2026-09-29","body_md":"Sources: https://docs.fish.audio/developer-guide/models-pricing/pricing-and-rate-limits , https://huggingface.co/fishaudio/s2-pro , https://fish.audio/blog/s2-1-pro-free-api/","page_url":"https://postcutoff.com/m/fish-audio-s2/","standing":{"kind":"speech and audio","newer_count":64,"newer":[{"id":"nemotron-3-5-transcribe","name":"NVIDIA Nemotron 3.5 Transcribe (30B-A4B)","org":"NVIDIA","released":"2026-10-28","page_url":"https://postcutoff.com/m/nemotron-3-5-transcribe/"},{"id":"hy-simulmt-30b-a3b","name":"Hy-SimulMT-30B-A3B","org":"Tencent","released":"2026-10-22","page_url":"https://postcutoff.com/m/hy-simulmt-30b-a3b/"},{"id":"eleven-realtime-v1-max","name":"Eleven Realtime v1 Max / Mini","org":"ElevenLabs","released":"2026-10-20","page_url":"https://postcutoff.com/m/eleven-realtime-v1-max/"},{"id":"voxtral-mini-transcribe-3","name":"Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3)","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-mini-transcribe-3/"},{"id":"voxtral-small-transcribe-3","name":"Voxtral Small Transcribe 3","org":"Mistral AI","released":"2026-10-20","page_url":"https://postcutoff.com/m/voxtral-small-transcribe-3/"}],"before":null,"after":{"id":"fish-audio-drama-3","name":"Fish Audio Drama 3","org":"Fish Audio","released":"2026-10-13","page_url":"https://postcutoff.com/m/fish-audio-drama-3/"},"weights":"public","licence":"Fish Audio Research License (S2 Pro weights; non-commercial, commercial license on request)","licence_permissive":false,"summary":"Weights are public. Licence: Fish Audio Research License. See the licence for commercial terms."}}