Fish Audio S2 Pro
Fish Audio · fishaudio/s2-pro
Weights license: Publisher terms: Fish Audio Research License · code and components may use other terms
Quality
No comparable score
Artificial Analysis score, rank and sample count excluded: its free tier is internal use only. Source checked 2026-09-22. Leaderboard (link only)
Reported by the publisher
Runs on
Enough memory 22
A publisher documents a path within this memory, on this platform (CUDA or Apple MPS). Conditional paths need offload or quantization.
Show all 22
One memory tier short 16
The same machines with the next memory size up would have enough.
Show all 16
Hardware profiles grouped by the publisher's documented minimum memory path and platform. Not a measured run.
Consider Fish Audio S2 Pro from Fish Audio for the text-to-speech task (4B parameters).
The catalog lists the publisher's documented memory path under Runs on and has not reviewed other configurations. Actual memory depends on precision, resolution, duration and offload; consult the official source.
Measured speed
No published measurement for this checkpoint
Speed (real-time factor, or seconds per clip) is shown only when a source publishes it with hardware, build and setup. It is never estimated.
How to run
Publisher-documented memory path: Official minimum recommendation for Fish Audio S2 inference. Actual memory depends on precision, resolution, duration and offload; consult the official source. Official hardware evidence
Documented ways to run it
Copied as printed in the linked source (read 2026-10-18); not run by this site.
hf download fishaudio/s2-pro --local-dir checkpoints/s2-propython tools/api_server.py \
--listen 0.0.0.0:8080 \
--llama-checkpoint-path checkpoints/s2-pro \
--decoder-checkpoint-path checkpoints/s2-pro/codec.pth \
--decoder-config-name modded_dac_vqEvidence level: Publisher documentation linked; no execution reproduced by this site.
Before downloading
- Check the exact checkpoint and license linked here.
- Confirm a compatible runtime and precision or quantization for your platform.
- Allow for context, batch size and any extra media components beyond the weights.
Technical details
What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.
- Checkpoint / version
- fishaudio/s2-pro
- Task and modality
- text-to-speech · audio
- Count and basis
- 4B · manufacturer model card
- Released
- Fish Audio S2 Technical Report (Fish Audio, arXiv 2603.08823, v1 submitted 2026-03-09; read through Hugging Face Papers) · read 2026-10-18source
- Published repository size
- 11 GBNot runtime memory or a minimum download.files
- Published components
- Technical details pending review
- Runtime and precision
- No local execution verified.
- Commercial use
- Not allowed Fish Audio Research License (fishaudio/s2-pro LICENSE.md) · read 2026-10-18license text
License, parameter count and release date come from the publisher's sources listed on this page (a date no source states is left empty). The hardware requirement has not been reviewed, so memory is a labelled estimate. The repository size, when shown, is the full published download.
Sources
Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.
- Publisher checkpoint and model card
- Weight license and use terms
- Quality benchmark source · Artificial Analysis audio · excluded (free tier is internal use only)
- Publisher hardware documentation
Catalog reviewed: 2026-09-22.






























