Fish Audio Open Models: Model List and Licenses
About Fish Audio
Fish Audio is a publisher of text-to-speech (TTS) models and services. It releases the open Fish Speech line of speech synthesis models on its fishaudio organization on Hugging Face.
What It Releases
- Fish Audio S2 Pro (March 2026): according to its model card, a text-to-speech model with fine-grained inline control of prosody and emotion, trained on more than 10 million hours of audio in 80+ languages, combining reinforcement learning alignment with a dual-autoregressive architecture.
- S1-mini (May 2025): a small speech synthesis model (gated).
- Fish Speech 1.x (2024): the earlier speech synthesis models from 1.0 to 1.5. There is also fish-agent-v0.1-3b, a voice conversation agent.
Licenses
Commercial use requires a separate agreement. The latest S2 Pro uses its own Fish Audio Research License, which allows research and non-commercial use free of charge, but commercial use requires a separate license from Fish Audio. S1-mini and Fish Speech 1.x are non-commercial CC BY-NC-SA 4.0. This summary is not legal advice; read each model’s license text before use.
Running Them Locally
- There are no official GGUF builds (as of 2026-09-26). Inference uses the fish-speech code on GitHub.
- If you are considering commercial use, mind the license. It is easy to use for personal trials and research, but using the generated audio commercially needs a separate agreement.
Sources: the model card and license text of fishaudio/s2-pro; the model list of the fishaudio organization on Hugging Face (all as of 2026-09-26).
Our Coverage and Data
Local Model Watch has not published an article on Fish Audio’s models yet. The model list below is collected by code from Hugging Face every day. Part of our publisher index; model families link to their family pages.
At a Glance
| Item | Value |
|---|---|
| Hugging Face organization | fishaudio |
| Models on Hugging Face | 9 |
| Articles on its own models | 0 |
| Articles on derived models | 0 |
Recent Models on Hugging Face
The publisher lists 9 models in total on Hugging Face. Below are up to 15 of the most recent generative models (text, image, video, audio and so on), the scope of this site, per organization. Classifiers, feature extractors, research components and repositories without a model card are omitted, and the publisher’s own quantized builds and helper variants are folded into the row of the original model. Parameter counts are left blank for repositories that pack weights into integer types, where Hugging Face’s count is not the real parameter count.
→ Scroll horizontally to see all columns
| Released | Model | Task | Parameters | License | Official variants |
|---|---|---|---|---|---|
| 2026-03-09 | fishaudio/s2-pro | audio | 4.6B | fish-audio-research-license |
— |
| 2025-05-31 | fishaudio/s1-mini | audio | — | cc-by-nc-sa-4.0 |
— |
| 2024-11-24 | fishaudio/fish-speech-1.5 | audio | — | cc-by-nc-sa-4.0 |
— |
| 2024-10-29 | fishaudio/fish-agent-v0.1-3b | audio | — | cc-by-nc-sa-4.0 |
— |
| 2024-09-10 | fishaudio/fish-speech-1.4 | audio | — | cc-by-nc-sa-4.0 |
— |
| 2024-07-18 | fishaudio/fish-speech-1.2-sft | audio | — | cc-by-nc-sa-4.0 |
— |
| 2024-07-02 | fishaudio/fish-speech-1.2 | audio | — | cc-by-nc-sa-4.0 |
— |
| 2024-04-19 | fishaudio/fish-speech-1 | audio | — | cc-by-nc-sa-4.0 |
— |
| 2023-12-07 | fishaudio/speech-lm-v1 | audio | — | cc-by-nc-sa-4.0 |
— |
From the Hugging Face API. Last changed 2026-09-27 (JST). Collected by code.
Last updated 2026-09-27 (JST). The explanation at the top of this page was written with the help of AI from the primary sources it cites. The tables and lists under “Our Coverage and Data" are assembled by code from our article log and the Hugging Face API.