univoice_
1 MCP server offers this tool
What it usually takes
cfg_scale– in 1 of 1nfe_steps– in 1 of 1randomize_seed– in 1 of 1reference_audio– in 1 of 1reference_text– in 1 of 1seed– in 1 of 1speed– in 1 of 1text– in 1 of 1
No server marks it as only reading: treat it as able to change data.
From each publisher's own tool list. We never call a tool.
Servers
| Server | Inputs | Read-only? |
|---|---|---|
UniVoice TTS co.huggingface.hugging-apps/univoice-tts-demo Clone the voice in a reference clip and make it read new text. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool. Returns: The synthesized 22.05 kHz waveform, and the seed that produced it. | cfg_scale,nfe_steps,randomize_seed,reference_audio,reference_text,seed,speed,text | Not stated |