voicekit_transcribe_audio – 2 MCP servers offer this tool
What it usually takes
audio_base64– in 2 of 2language– in 2 of 2
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? |
|---|---|---|
VoiceKit MCP co.huggingface.mcp-1st-birthday/voicekit Convert audio to text (Speech-to-Text). Uses ElevenLabs Scribe v1 model for high-quality speech recognition. Supports various languages. Returns: text, language, model | audio_base64,language | Not stated |
VoiceKit MCP co.huggingface.brickhousestudiosllc/voicekit Placeholder transcription lane. Real ASR is not wired in real-dsp-v1. | audio_base64,language | Not stated |