Fish-Audio-S2-Pro-NVFP4-Balanced

ajh-code/Fish-Audio-S2-Pro-NVFP4-Balanced

Text to Speech3.9B parametersfish-speechLicense: other

Tracked by OpenModelStats since September 7, 2026View on Hugging Face ↗

Downloads 30D: 124
Total downloads: 124
Gained 7D: +104(increase)
Gained 30D: —
Likes: 1; +1 in 7D
Rank · tracked models: —; –this week
Parameters: 3.9B
Last source update: Aug 27, 2026

Fish-Audio-S2-Pro-NVFP4-Balanced gained 104 downloads during the last seven tracked days.

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-07. Charts appear as daily observations accumulate.

Overview

Fish-Audio-S2-Pro-NVFP4-Balanced is a text to speech model published by ajh-code. OpenModelStats has tracked the model since Sep 7, 2026, most recently observing it Sep 24, 2026.

Published: Aug 27, 2026
Last updated: Aug 27, 2026
Library: fish-speech
License: other
Task: Text to Speech
Parameters: 3,924,842,496
Spaces: —
Derivative models: —
Velocity 7D/day: 15

fish-speechsafetensorsfish_qwen3_omnifish-audiotext-to-speechvoice-cloningquantizationnvfp4mxfp8blackwellsm120english

Publisher

ajh-codeView publisher statistics →

Derived from fishaudio/s2-pro (reported by the source; parent not yet tracked).

Similar models

Models similar to Fish-Audio-S2-Pro-NVFP4-Balanced
Model	Task	DL 30D	Likes	Params
Voxtral-4B-TTS-2603-mlx-6bitmlx-community	Text to Speech	826	5	4B
Llasa-3BHKUSTAudio	Text to Speech	318	531	4B
LongCat-AudioDiT-3.5B-bf16drbaph	Text to Speech	5,680	6	3.8B
Veenamaya-research	Text to Speech	3,880	240	3.8B
orpheus-3b-0.1-ftcanopylabs	Text to Speech	30.7K	745	3.8B
orpheus-3b-0.1-ftjetjodh	Text to Speech	5,300	0	3.8B