Fish Audio Drama 3
Fish Audio Drama 3 is a text-to-speech model designed for multi-character scenes and long-form content. It supports voice cloning, natural-language control, and generation with up to 16 speaker tags.
What it does
Use it to generate streaming speech for long-form or multi-character content, including speech that clones a voice from a reference clip.
- Availability
- Available on Hugging Face; serving instructions are provided for SGLang-Omni and vLLM-Omni.
- Pricing model
- Not established
- Deployment
- Can be served with SGLang-Omni or vLLM-Omni.
- Privacy
- Not established
- Licence
- Fish Audio Community License
Capability
Modality
Access
Deployment
Pricing
Target user
Evidence
5 claims- The model supports multi-speaker generation, voice cloning, and natural-language control. [1]
It supports multi-speaker generation, voice cloning and
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Speaker tags allow one text input to carry up to 16 characters. [1]
- **Speaker tags** `<|speaker:0|>` … `<|speaker:15|>` — one text can carry up to 16 characters
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Long text is chunked automatically and can be streamed per chunk. [1]
- **Long text** is chunked automatically and can be streamed per chunk
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - Drama 3 can be served with SGLang-Omni and vLLM-Omni. [1]
For installation, deployment, and streaming API examples, see the [Drama 3 Cookbook](https://sgl-project.github.io/sglang-omni/cookbook/fishaudio_drama3.html).
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights. - The model is licensed under the Fish Audio Community License. [1]
This model is licensed under the [Fish Audio Community License](https://huggingface.co/fishaudio/drama-3/blob/main/LICENSE).
Hugging Face. Quoted text is outside CC BY 4.0 and keeps its original rights.
Sources
1
1
Hugging FaceOwner-controlled
https://huggingface.co/fishaudio/drama-3
Retrieved 2026-10-28 00:39 UTC
Verified
Versions
3| Version | Effective | Change | Changed fields | State |
|---|---|---|---|---|
| 3 | 2026-10-17 07:33 UTC | material change | availability, deployment | Current |
| 2 | 2026-10-15 09:21 UTC | material change | availability, deployment | Current |
| 1 | 2026-10-14 10:20 UTC | publication | None | Current |
In briefs
1- Extract structured text from PDFs and images on a CPU Daily brief 2026-10-14
Original catalog content is licensed under CC BY 4.0, attributed to wowsuchai. Source quotations and linked content keep their original rights.