🧠
Model

Fishaudio S2 Pro 8bit Mlx

by appautomaton hf-model--appautomaton--fishaudio-s2-pro-8bit-mlx
Nexus Index
39.7 Top 100%
S: Semantic 50
A: Authority 0
P: Popularity 11
R: Recency 97
Q: Quality 65
Tech Context
8 Params
4.096K Ctx
Vital Performance
328 DL / 30D
0.0%
Audited 39.7 FNI Score
8B Params
4k Context
328 Downloads
8G GPU ~8GB Est. VRAM
Restricted OTHER License
Model Information Summary
Entity Passport
Registry ID hf-model--appautomaton--fishaudio-s2-pro-8bit-mlx
License Other
Provider huggingface
💾

Compute Threshold

~7.3GB VRAM

Interactive
Analyze Hardware
â–ŧ

* Static estimation for 4-Bit Quantization.

📜

Cite this model

Academic & Research Attribution

BibTeX
@misc{hf_model__appautomaton__fishaudio_s2_pro_8bit_mlx,
  author = {appautomaton},
  title = {Fishaudio S2 Pro 8bit Mlx Model},
  year = {2026},
  howpublished = {\url{https://huggingface.co/appautomaton/fishaudio-s2-pro-8bit-mlx}},
  note = {Accessed via Free2AITools Knowledge Fortress}
}
APA Style
appautomaton. (2026). Fishaudio S2 Pro 8bit Mlx [Model]. Free2AITools. https://huggingface.co/appautomaton/fishaudio-s2-pro-8bit-mlx

đŸ”ŦTechnical Deep Dive

Full Specifications [+]

Quick Commands

đŸĻ™ Ollama Run
ollama run fishaudio-s2-pro-8bit-mlx
🤗 HF Download
huggingface-cli download appautomaton/fishaudio-s2-pro-8bit-mlx

âš–ī¸ Nexus Index V2.0

39.7
TOP 100% SYSTEM IMPACT
Semantic (S) 50
Authority (A) 0
Popularity (P) 11
Recency (R) 97
Quality (Q) 65

đŸ’Ŧ Index Insight

FNI V2.0 for Fishaudio S2 Pro 8bit Mlx: Semantic (S:50), Authority (A:0), Popularity (P:11), Recency (R:97), Quality (Q:65).

Free2AITools Nexus Index

Verification Authority

Unbiased Data Node Refresh: VFS Live
---

🚀 What's Next?

Technical Deep Dive

Fish Audio S2 Pro — MLX 8-bit

This repository contains a self-contained MLX-native int8 conversion of Fish Audio S2 Pro for local text-to-speech on Apple Silicon.

It is intended for local speech generation with mlx-speech, without a PyTorch runtime at inference time.

Model Details

  • Developed by: AppAutomaton
  • Shared by: AppAutomaton on Hugging Face
  • Upstream model: fishaudio/s2-pro
  • Task: text-to-speech and voice cloning
  • Runtime: MLX on Apple Silicon
  • Precision: int8 main model weights with bundled MLX codec assets

Bundle Contents

This bundle is self-contained and includes:

  • config.json
  • model.safetensors
  • tokenizer files
  • codec-mlx/config.json
  • codec-mlx/model.safetensors

The Fish S2 Pro runtime uses the bundled codec-mlx/ directory to decode model codes into waveform output.

How to Get Started

Basic generation:

bash
python scripts/generate/fish_s2_pro.py \
  --text "Hello from Fish S2 Pro." \
  --model-dir /path/to/fishaudio-s2-pro-8bit-mlx \
  --output outputs/fish_s2_pro.wav

Voice cloning:

bash
python scripts/generate/fish_s2_pro.py \
  --text "This is a cloned voice." \
  --reference-audio /path/to/reference.wav \
  --reference-text "Transcript of the reference audio." \
  --model-dir /path/to/fishaudio-s2-pro-8bit-mlx \
  --output outputs/fish_s2_pro_clone.wav

Inline prosody and emotion tags:

Fish S2 Pro supports 15,000+ inline tags placed directly in the text. Tags are single open-style [tag] — no closing tag. Place them immediately before the word or phrase they apply to.

bash
python scripts/generate/fish_s2_pro.py \
  --text "Now Bobby, [clearing throat] I need to talk to you. [whisper] This stays between us. [chuckle] Just kidding." \
  --reference-audio /path/to/reference.wav \
  --reference-text "Transcript of the reference audio." \
  --output outputs/fish_s2_pro_emotion.wav

Common tags: [whisper], [chuckle], [laugh], [clearing throat], [excited], [sad], [pause]. See the upstream repo for the full tag list.

Minimal Python usage:

python
from pathlib import Path

from mlx_speech.generation.fish_s2_pro import generate_fish_s2_pro

result = generate_fish_s2_pro(
    "Hello from Fish S2 Pro.",
    model_dir=Path("/path/to/fishaudio-s2-pro-8bit-mlx"),
)

Notes

  • This repo contains the quantized MLX runtime artifact only.
  • The conversion keeps the Fish S2 Pro dual-autoregressive model architecture and ships a bundled MLX codec for waveform decode.
  • Upstream defaults: temperature=0.8, top_p=0.8.
  • The current bundle is intended for local MLX runtime use and parity validation.

License

Fish Audio Research License — following the upstream license published with fishaudio/s2-pro.

âš ī¸ Incomplete Data

Some information about this model is not available. Use with Caution - Verify details from the original source before relying on this data.

View Original Source →

📝 Limitations & Considerations

  • â€ĸ Benchmark scores may vary based on evaluation methodology and hardware configuration.
  • â€ĸ VRAM requirements are estimates; actual usage depends on quantization and batch size.
  • â€ĸ FNI scores are relative rankings and may change as new models are added.
  • ⚠ License Unknown: Verify licensing terms before commercial use.

Social Proof

HuggingFace Hub
328Downloads
🔄 Daily sync (03:00 UTC)

AI Summary: Based on Hugging Face metadata. Not a recommendation.

📊 FNI Methodology 📚 Knowledge Baseâ„šī¸ Verify with original source

đŸ›Ąī¸ Model Transparency Report

Technical metadata sourced from upstream repositories.

Open Metadata

🆔 Identity & Source

id
hf-model--appautomaton--fishaudio-s2-pro-8bit-mlx
slug
appautomaton--fishaudio-s2-pro-8bit-mlx
source
huggingface
author
appautomaton
license
Other
tags
mlx, safetensors, fish_qwen3_omni, tts, speech, fishaudio, fish-s2-pro, quantized, int8, apple-silicon, bundled-codec, text-to-speech, base_model:fishaudio/s2-pro, base_model:quantized:fishaudio/s2-pro, license:other, region:us

âš™ī¸ Technical Specs

architecture
null
params billions
8
context length
4,096
pipeline tag
text-to-speech
vram gb
7.3
vram is estimated
true
vram formula
VRAM ≈ (params * 0.75) + 0.8GB (KV) + 0.5GB (OS)

📊 Engagement & Metrics

downloads
328
stars
0
forks
0

Data indexed from public sources. Updated daily.