fishaudio/s2-pro
text-to-speech model by fishaudio
From the publisher
Model card & documentation
Source previewRead the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.
Technical Report | GitHub | Playground Fish Audio S2 Pro is a leading text-to-speech (TTS) model with fine-grained inline control of prosody and emotion. Trained on over 10M+ hours of audio data across 80+ languages, the system combines reinforcement learning alignment with a dual-autoregressive architecture. The release includes model weights, fine-tuning code, and an SGLang-based streaming inference engine. S2 Pro builds on a decoder-only transformer combined with an RVQ-based audio codec (10 codebooks, 21 Hz frame rate) using a Dual-Autoregressive (Dual-AR) architecture: This asymmetric design keeps inference efficient while preserving audio fidelity. Because the Dual-AR architecture is structurally isomorphic to standard autoregressive LLMs, it inherits all LLM-native serving optimizations from SGLang — including continuous batching, paged KV cache, CUDA graph replay, and RadixAttention-based prefix caching. S2 Pro enables localized control over speech generation by embedding natural-language instructions directly within the text using [tag] syntax. Rather than relying on a fixed…
Read the full model card ↗ · Preview checked 2026-10-28T03:10:49.956Z
Inside the original model card — Document outline
- Fish Audio S2 Pro
- Architecture
- Fine-Grained Inline Control
- Supported Languages
- Production Streaming Performance
- Links
- Technical Report
- License
Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.
Links from the model card
References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.
Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.
Model overview
fishaudio/s2-pro is a text-to-speech model repository published by fishaudio on Hugging Face. A library was not reported.
This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.
Model facts
- Task
- text-to-speech
- Library
- Not reported
- Recent downloads (30 days)
- 48,020
- Cumulative likes
- 1,486
- Hugging Face trending score
- 14
- Reported safetensors parameters
- 4,561,852,416
- Architecture
- Not reported
- License
- other
- Access
- Not gated by Hugging Face
- Created
- 2026-03-09T05:48:58.000Z
- Last modified
- 2026-03-11T15:32:58.000Z
Compatibility and lineage
Reported languages: zh, en, ja, ko, es, pt, ar, ru, fr, de, sv, it, tr, no, nl, cy, eu, ca, da, gl, ta, hu, fi, pl, et, hi, la, ur, th, vi, jw, bn, yo, sl, cs, sw, nn, he, ms, uk
Base-model lineage was not included.
Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.
Use and evaluate
Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.
No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.
Source and freshness
Source: Hugging Face Hub. Metadata observed 2026-11-01T06:52:33.137Z. Daily imports are snapshots, not real-time monitoring.
Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.