Qwen3_
1 MCP server offers this tool
What it usually takes
language– in 1 of 1text– in 1 of 1voice_description– 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 Demo co.huggingface.katyado/qwen3-tts Generate speech using Voice Design model (1.7B only). | language,text,voice_description | Not stated |