kokoro_
1 MCP server offers this tool
What it usually takes
speed– in 1 of 1text– in 1 of 1voice– 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? |
|---|---|---|
Kokoro Ja co.huggingface.hayas/kokoro-ja Synthesizes speech from Japanese text using the Kokoro TTS model. Note: This model supports only Japanese input texts. Voice Selection: - The `voice` parameter specifies the speaker's characteristics and should follow the naming convention: `<language/accent><gender>_<voice_name>` - `<language/accent>`: - 'j' for Japanese - `<gender>`: - 'f' for female - 'm' for male - Example: 'jf_alpha' indicates an Japanese female voice named Alpha. Available voices: - jf_alpha - jf_gongitsune - jf_nezumi - jf_tebukuro - jm_kumo. Returns: A tuple containing the audio and the tokens used to generate the audio. | speed,text,voice | Not stated |