plug.directory

qwen3_tts_ru_stress_generate

1 MCP server offers this tool

What it usually takes

auto_stress – in 1 of 1
max_new_tokens – in 1 of 1
randomize_seed – in 1 of 1
ref_audio – in 1 of 1
ref_text – in 1 of 1
repetition_penalty – in 1 of 1
seed – in 1 of 1
temperature – in 1 of 1
text – in 1 of 1
top_k – in 1 of 1
top_p – in 1 of 1
x_vector_only – 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?
Qwen3-TTS Russian Stress Voice Cloning `co.huggingface.hugging-apps/qwen3-tts-ru-stress` Synthesize Russian speech in a cloned voice, obeying stress marks. 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: Tuple of (audio filepath at 24kHz, used_seed, synthesis_seconds).	`auto_stress`,`max_new_tokens`,`randomize_seed`,`ref_audio`,`ref_text`,`repetition_penalty`,`seed`,`temperature`,`text`,`top_k`,`top_p`,`x_vector_only`	Not stated