Text-to-Speech
GGUF
quantized
conversational

s2-pro

Run it from the terminal:

llama-tts -hf ggml-org/s2-pro-GGUF -p "<|speaker:0|>Hello world [laughing]" --output out.wav

Or with the server, using the /tts endpoint:

llama serve -hf ggml-org/s2-pro-GGUF

Source models

Notes

The weights are released under the Fish Audio Research License: free for research and non-commercial use, commercial use is limited, see the license.

This model is automatically converted using https://github.com/ggml-org/convert

Downloads last month
764
GGUF
Model size
4B params
Architecture
qwen3
Hardware compatibility
Log In to add your hardware

8-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for ggml-org/s2-pro-GGUF

Base model

fishaudio/s2-pro
Quantized
(17)
this model

Collection including ggml-org/s2-pro-GGUF