nefes_ expressive_ turkish_ tts_ speak
1 MCP server offers this tool
What it usually takes
candidates– 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? |
|---|---|---|
Nefes 0.5 co.huggingface.hugging-apps/nefes-expressive-turkish-tts Synthesize expressive Turkish speech from text with inline emotion tags. Returns: Tuple of (audio path at 48 kHz, info string). | candidates,text | Not stated |