--- base_model: fishaudio/s2-pro base_model_relation: quantized license: other license_name: fish-audio-research-license license_link: LICENSE.md pipeline_tag: text-to-speech library_name: mlx-audio tags: - mlx - moonbox - mlx-audio - fish-audio - fish-speech - s2-pro - text-to-speech - voice-cloning - multilingual --- # Fish Audio S2 Pro MLX MLX builds of [Fish Audio S2 Pro](https://huggingface.co/fishaudio/s2-pro), made by Moonbox for Apple Silicon Macs. Each precision is a folder; keep a folder's files together. Only the parts listed below are converted: the rest of the pipeline comes from the original repository unless the section below says otherwise. ## Files The last column is how far each build is from the original PyTorch model on the same inputs (see the section below for what was measured). | Precision | File | Size | sha256 | Checked against the original | |---|---|---|---|---| | bf16 | [`bf16/chat_template.jinja`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/bf16/chat_template.jinja) | 4.1 kB | `87a2728cb8dc` | WER 0.0 % / CER 0.0 %, speaker sim 0.956 / 0.952, DNSMOS 3.24 / 2.92 (original 0.0 % / 0.0 %, 0.952 / 0.949, 3.21 / 2.76) | | bf16 | [`bf16/codec.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/bf16/codec.safetensors) | 2.78 GB | `fde06aa1f23b` | WER 0.0 % / CER 0.0 %, speaker sim 0.956 / 0.952, DNSMOS 3.24 / 2.92 (original 0.0 % / 0.0 %, 0.952 / 0.949, 3.21 / 2.76) | | bf16 | [`bf16/config.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/bf16/config.json) | 2.1 kB | `870046f617ca` | WER 0.0 % / CER 0.0 %, speaker sim 0.956 / 0.952, DNSMOS 3.24 / 2.92 (original 0.0 % / 0.0 %, 0.952 / 0.949, 3.21 / 2.76) | | bf16 | [`bf16/model-00001-of-00002.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/bf16/model-00001-of-00002.safetensors) | 5.35 GB | `13c1b614ac67` | WER 0.0 % / CER 0.0 %, speaker sim 0.956 / 0.952, DNSMOS 3.24 / 2.92 (original 0.0 % / 0.0 %, 0.952 / 0.949, 3.21 / 2.76) | | bf16 | [`bf16/model-00002-of-00002.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/bf16/model-00002-of-00002.safetensors) | 3.78 GB | `a75a5d2e91dd` | WER 0.0 % / CER 0.0 %, speaker sim 0.956 / 0.952, DNSMOS 3.24 / 2.92 (original 0.0 % / 0.0 %, 0.952 / 0.949, 3.21 / 2.76) | | bf16 | [`bf16/model.safetensors.index.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/bf16/model.safetensors.index.json) | 30.4 kB | `65dc730b4e46` | WER 0.0 % / CER 0.0 %, speaker sim 0.956 / 0.952, DNSMOS 3.24 / 2.92 (original 0.0 % / 0.0 %, 0.952 / 0.949, 3.21 / 2.76) | | bf16 | [`bf16/special_tokens_map.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/bf16/special_tokens_map.json) | 0.1 MB | `c2ff18fde6e4` | WER 0.0 % / CER 0.0 %, speaker sim 0.956 / 0.952, DNSMOS 3.24 / 2.92 (original 0.0 % / 0.0 %, 0.952 / 0.949, 3.21 / 2.76) | | bf16 | [`bf16/tokenizer.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/bf16/tokenizer.json) | 12.2 MB | `f24e08099d45` | WER 0.0 % / CER 0.0 %, speaker sim 0.956 / 0.952, DNSMOS 3.24 / 2.92 (original 0.0 % / 0.0 %, 0.952 / 0.949, 3.21 / 2.76) | | bf16 | [`bf16/tokenizer_config.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/bf16/tokenizer_config.json) | 0.9 MB | `b8d149343ae4` | WER 0.0 % / CER 0.0 %, speaker sim 0.956 / 0.952, DNSMOS 3.24 / 2.92 (original 0.0 % / 0.0 %, 0.952 / 0.949, 3.21 / 2.76) | | fp16 | [`fp16/chat_template.jinja`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/fp16/chat_template.jinja) | 4.1 kB | `87a2728cb8dc` | WER 0.0 % / CER 0.0 %, speaker sim 0.964 / 0.951, DNSMOS 3.21 / 2.86 | | fp16 | [`fp16/codec.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/fp16/codec.safetensors) | 2.78 GB | `fde06aa1f23b` | WER 0.0 % / CER 0.0 %, speaker sim 0.964 / 0.951, DNSMOS 3.21 / 2.86 | | fp16 | [`fp16/config.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/fp16/config.json) | 2.1 kB | `870046f617ca` | WER 0.0 % / CER 0.0 %, speaker sim 0.964 / 0.951, DNSMOS 3.21 / 2.86 | | fp16 | [`fp16/model-00001-of-00002.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/fp16/model-00001-of-00002.safetensors) | 5.35 GB | `d70c8e348abd` | WER 0.0 % / CER 0.0 %, speaker sim 0.964 / 0.951, DNSMOS 3.21 / 2.86 | | fp16 | [`fp16/model-00002-of-00002.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/fp16/model-00002-of-00002.safetensors) | 3.78 GB | `94b99c94994c` | WER 0.0 % / CER 0.0 %, speaker sim 0.964 / 0.951, DNSMOS 3.21 / 2.86 | | fp16 | [`fp16/model.safetensors.index.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/fp16/model.safetensors.index.json) | 30.4 kB | `65dc730b4e46` | WER 0.0 % / CER 0.0 %, speaker sim 0.964 / 0.951, DNSMOS 3.21 / 2.86 | | fp16 | [`fp16/special_tokens_map.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/fp16/special_tokens_map.json) | 0.1 MB | `c2ff18fde6e4` | WER 0.0 % / CER 0.0 %, speaker sim 0.964 / 0.951, DNSMOS 3.21 / 2.86 | | fp16 | [`fp16/tokenizer.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/fp16/tokenizer.json) | 12.2 MB | `f24e08099d45` | WER 0.0 % / CER 0.0 %, speaker sim 0.964 / 0.951, DNSMOS 3.21 / 2.86 | | fp16 | [`fp16/tokenizer_config.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/fp16/tokenizer_config.json) | 0.9 MB | `b8d149343ae4` | WER 0.0 % / CER 0.0 %, speaker sim 0.964 / 0.951, DNSMOS 3.21 / 2.86 | | 8bit | [`8bit/chat_template.jinja`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/8bit/chat_template.jinja) | 4.1 kB | `87a2728cb8dc` | WER 0.0 % / CER 0.0 %, speaker sim 0.953 / 0.953, DNSMOS 3.22 / 2.83 | | 8bit | [`8bit/codec.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/8bit/codec.safetensors) | 2.78 GB | `fde06aa1f23b` | WER 0.0 % / CER 0.0 %, speaker sim 0.953 / 0.953, DNSMOS 3.22 / 2.83 | | 8bit | [`8bit/config.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/8bit/config.json) | 2.3 kB | `363895eff17c` | WER 0.0 % / CER 0.0 %, speaker sim 0.953 / 0.953, DNSMOS 3.22 / 2.83 | | 8bit | [`8bit/model-00001-of-00002.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/8bit/model-00001-of-00002.safetensors) | 5.35 GB | `7d96671b6003` | WER 0.0 % / CER 0.0 %, speaker sim 0.953 / 0.953, DNSMOS 3.22 / 2.83 | | 8bit | [`8bit/model-00002-of-00002.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/8bit/model-00002-of-00002.safetensors) | 372.3 MB | `876e059805ce` | WER 0.0 % / CER 0.0 %, speaker sim 0.953 / 0.953, DNSMOS 3.22 / 2.83 | | 8bit | [`8bit/model.safetensors.index.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/8bit/model.safetensors.index.json) | 61.0 kB | `7815620c53eb` | WER 0.0 % / CER 0.0 %, speaker sim 0.953 / 0.953, DNSMOS 3.22 / 2.83 | | 8bit | [`8bit/special_tokens_map.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/8bit/special_tokens_map.json) | 0.1 MB | `c2ff18fde6e4` | WER 0.0 % / CER 0.0 %, speaker sim 0.953 / 0.953, DNSMOS 3.22 / 2.83 | | 8bit | [`8bit/tokenizer.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/8bit/tokenizer.json) | 12.2 MB | `f24e08099d45` | WER 0.0 % / CER 0.0 %, speaker sim 0.953 / 0.953, DNSMOS 3.22 / 2.83 | | 8bit | [`8bit/tokenizer_config.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/8bit/tokenizer_config.json) | 0.9 MB | `b8d149343ae4` | WER 0.0 % / CER 0.0 %, speaker sim 0.953 / 0.953, DNSMOS 3.22 / 2.83 | | 6bit | [`6bit/chat_template.jinja`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/6bit/chat_template.jinja) | 4.1 kB | `87a2728cb8dc` | WER 0.0 % / CER 0.0 %, speaker sim 0.966 / 0.945, DNSMOS 3.24 / 2.80 | | 6bit | [`6bit/codec.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/6bit/codec.safetensors) | 2.78 GB | `fde06aa1f23b` | WER 0.0 % / CER 0.0 %, speaker sim 0.966 / 0.945, DNSMOS 3.24 / 2.80 | | 6bit | [`6bit/config.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/6bit/config.json) | 2.3 kB | `e26146aa01b3` | WER 0.0 % / CER 0.0 %, speaker sim 0.966 / 0.945, DNSMOS 3.24 / 2.80 | | 6bit | [`6bit/model.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/6bit/model.safetensors) | 4.81 GB | `1c8b473cc7a9` | WER 0.0 % / CER 0.0 %, speaker sim 0.966 / 0.945, DNSMOS 3.24 / 2.80 | | 6bit | [`6bit/model.safetensors.index.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/6bit/model.safetensors.index.json) | 50.2 kB | `dc9f4a81f88b` | WER 0.0 % / CER 0.0 %, speaker sim 0.966 / 0.945, DNSMOS 3.24 / 2.80 | | 6bit | [`6bit/special_tokens_map.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/6bit/special_tokens_map.json) | 0.1 MB | `c2ff18fde6e4` | WER 0.0 % / CER 0.0 %, speaker sim 0.966 / 0.945, DNSMOS 3.24 / 2.80 | | 6bit | [`6bit/tokenizer.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/6bit/tokenizer.json) | 12.2 MB | `f24e08099d45` | WER 0.0 % / CER 0.0 %, speaker sim 0.966 / 0.945, DNSMOS 3.24 / 2.80 | | 6bit | [`6bit/tokenizer_config.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/6bit/tokenizer_config.json) | 0.9 MB | `b8d149343ae4` | WER 0.0 % / CER 0.0 %, speaker sim 0.966 / 0.945, DNSMOS 3.24 / 2.80 | | 4bit | [`4bit/chat_template.jinja`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/4bit/chat_template.jinja) | 4.1 kB | `87a2728cb8dc` | WER 0.0 % / CER 0.0 %, speaker sim 0.963 / 0.944, DNSMOS 3.22 / 3.01 | | 4bit | [`4bit/codec.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/4bit/codec.safetensors) | 2.78 GB | `fde06aa1f23b` | WER 0.0 % / CER 0.0 %, speaker sim 0.963 / 0.944, DNSMOS 3.22 / 3.01 | | 4bit | [`4bit/config.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/4bit/config.json) | 2.3 kB | `04a6afe6a550` | WER 0.0 % / CER 0.0 %, speaker sim 0.963 / 0.944, DNSMOS 3.22 / 3.01 | | 4bit | [`4bit/model.safetensors`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/4bit/model.safetensors) | 3.90 GB | `f57eb1c13b76` | WER 0.0 % / CER 0.0 %, speaker sim 0.963 / 0.944, DNSMOS 3.22 / 3.01 | | 4bit | [`4bit/model.safetensors.index.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/4bit/model.safetensors.index.json) | 50.2 kB | `5c1dd949a15f` | WER 0.0 % / CER 0.0 %, speaker sim 0.963 / 0.944, DNSMOS 3.22 / 3.01 | | 4bit | [`4bit/special_tokens_map.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/4bit/special_tokens_map.json) | 0.1 MB | `c2ff18fde6e4` | WER 0.0 % / CER 0.0 %, speaker sim 0.963 / 0.944, DNSMOS 3.22 / 3.01 | | 4bit | [`4bit/tokenizer.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/4bit/tokenizer.json) | 12.2 MB | `f24e08099d45` | WER 0.0 % / CER 0.0 %, speaker sim 0.963 / 0.944, DNSMOS 3.22 / 3.01 | | 4bit | [`4bit/tokenizer_config.json`](https://huggingface.co/moonbox-dev/s2-pro-MLX/blob/main/4bit/tokenizer_config.json) | 0.9 MB | `b8d149343ae4` | WER 0.0 % / CER 0.0 %, speaker sim 0.963 / 0.944, DNSMOS 3.22 / 3.01 | ## How to run Fish Audio S2 Pro (4.4B dual-autoregressive TTS: voice cloning, 80+ languages, inline `[tag]` control of emotion and prosody) for [mlx-audio](https://github.com/Blaizzy/mlx-audio). **Built with Fish Audio.** Each folder is a complete mlx-audio model: `model-*.safetensors` (slow and fast AR transformers), `codec.safetensors` (the DAC codec, float32, re-saved unchanged from the original `codec.pth`), the tokenizer and chat template. Tested with `mlx-audio==0.6.5`: ```python from mlx_audio.tts.utils import load_model import mlx.core as mx, numpy as np, soundfile as sf, librosa model = load_model("8bit") # a downloaded folder ref = mx.array(librosa.load("voice.wav", sr=model.sample_rate)[0]) res = list(model.generate(text="Hello from Moonbox.", ref_audio=ref, ref_text="Exact transcript of voice.wav.")) sf.write("out.wav", np.concatenate([np.array(r.audio) for r in res]), res[0].sample_rate) ``` `8bit/`, `6bit/` and `4bit/` quantize the transformer layers (MLX affine, group size 64); the codec is not quantized. **License:** Fish Audio Research License: research and non-commercial use only; commercial use needs a license from Fish Audio. See `LICENSE.md` and `NOTICE.md` (what was changed). **How they were checked.** Voice cloning of 6 English and 4 Chinese sentences, two seeds each, with the original (fish-speech's own inference code, PyTorch bfloat16) and every MLX build, the original's sampling (temperature 0.7, top-p 0.7, top-k 30). Judged like the original: Whisper large-v3-turbo WER / CER, WavLM speaker similarity to the prompt, DNSMOS. Pass: error rate at most 2 points above the original's, similarity at most 0.03 below, DNSMOS at most 0.2 below. | Precision | Size | WER en / CER zh | Speaker similarity en / zh | DNSMOS en / zh | Real-time factor, M5 24 GB | |---|---|---|---|---|---| | original (PyTorch bf16, MPS) | - | 0.0 % / 0.0 % | 0.952 / 0.949 | 3.21 / 2.76 | 4.2 | | `bf16/` | 11.9 GB | 0.0 % / 0.0 % | 0.956 / 0.952 | 3.24 / 2.92 | ~5 | | `fp16/` | 11.9 GB | 0.0 % / 0.0 % | 0.964 / 0.951 | 3.21 / 2.86 | 4.7 | | `8bit/` | 8.5 GB | 0.0 % / 0.0 % | 0.953 / 0.953 | 3.22 / 2.83 | 3.2 | | `6bit/` | 7.6 GB | 0.0 % / 0.0 % | 0.966 / 0.945 | 3.24 / 2.80 | 3.1 | | `4bit/` | 6.7 GB | 0.0 % / 0.0 % | 0.963 / 0.944 | 3.22 / 3.01 | 3.0 | Real-time factor = generation time / audio length, one sentence at a time (slower than real time on a 24 GB M5). ## How these were made From [Fish Audio S2 Pro](https://huggingface.co/fishaudio/s2-pro) at revision `1de9996b6b`: the original weights loaded in MLX and stored as bf16 or fp16, or quantized with MLX's affine quantization (`8bit`, `6bit`, `4bit`, group size 64; layers MLX can't quantize, such as convolutions and norms, stay bf16). Every build was checked against the original before upload; the `sha256` column above is what the files must hash to. ## License other (Fish Audio research license). These files are a derivative of the original model and carry its license: it is copied in this repository, and it governs your use of these files. The original model card follows unchanged. --- # Original model card # Fish Audio S2 Pro Fish Audio S2 Pro overview — fine-grained control, multi-speaker multi-turn generation, low-latency streaming, and long-context inference. [**Technical Report**](https://huggingface.co/papers/2603.08823) | [**GitHub**](https://github.com/fishaudio/fish-speech) | [**Playground**](https://fish.audio) **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. ## Architecture 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: - **Slow AR** (4B parameters): Operates along the time axis and predicts the primary semantic codebook. - **Fast AR** (400M parameters): Generates the remaining 9 residual codebooks at each time step, reconstructing fine-grained acoustic detail. 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. ## Fine-Grained Inline Control 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 set of predefined tags, S2 Pro accepts **free-form textual descriptions** — such as `[whisper in small voice]`, `[professional broadcast tone]`, or `[pitch up]` — allowing open-ended expression control at the word level. **Common tags (15,000+ unique tags supported):** `[pause]` `[emphasis]` `[laughing]` `[inhale]` `[chuckle]` `[tsk]` `[singing]` `[excited]` `[laughing tone]` `[interrupting]` `[chuckling]` `[excited tone]` `[volume up]` `[echo]` `[angry]` `[low volume]` `[sigh]` `[low voice]` `[whisper]` `[screaming]` `[shouting]` `[loud]` `[surprised]` `[short pause]` `[exhale]` `[delight]` `[panting]` `[audience laughter]` `[with strong accent]` `[volume down]` `[clearing throat]` `[sad]` `[moaning]` `[shocked]` ## Supported Languages S2 Pro supports 80+ languages. **Tier 1:** Japanese (ja), English (en), Chinese (zh) **Tier 2:** Korean (ko), Spanish (es), Portuguese (pt), Arabic (ar), Russian (ru), French (fr), German (de) **Other supported languages:** sv, it, tr, no, nl, cy, eu, ca, da, gl, ta, hu, fi, pl, et, hi, la, ur, th, vi, jw, bn, yo, xsl, cs, sw, nn, he, ms, uk, id, kk, bg, lv, my, tl, sk, ne, fa, af, el, bo, hr, ro, sn, mi, yi, am, be, km, is, az, sd, br, sq, ps, mn, ht, ml, sr, sa, te, ka, bs, pa, lt, kn, si, hy, mr, as, gu, fo, and more. ## Production Streaming Performance On a single NVIDIA H200 GPU: - **Real-Time Factor (RTF):** 0.195 - **Time-to-first-audio:** ~100 ms - **Throughput:** 3,000+ acoustic tokens/s while maintaining RTF below 0.5 ## Links - [Fish Speech GitHub](https://github.com/fishaudio/fish-speech) - [Fish Audio Playground](https://fish.audio) - [Blog & Tech Report](https://fish.audio/blog/fish-audio-open-sources-s2/) ## Technical Report If you find our work useful, please consider citing our report: ```bibtex @misc{liao2026fishaudios2technical, title={Fish Audio S2 Technical Report}, author={Shijia Liao and Yuxuan Wang and Songting Liu and Yifan Cheng and Ruoyi Zhang and Tianyu Li and Shidong Li and Yisheng Zheng and Xingwei Liu and Qingzheng Wang and Zhizhuo Zhou and Jiahua Liu and Xin Chen and Dawei Han}, year={2026}, eprint={2603.08823}, archivePrefix={arXiv}, primaryClass={cs.SD}, url={https://arxiv.org/abs/2603.08823}, } ``` ## License This model is licensed under the [Fish Audio Research License](LICENSE.md). Research and non-commercial use is permitted free of charge. Commercial use requires a separate license from Fish Audio — contact business@fish.audio.