About Vibevoice Server
Vibevoice Server is an MCP server in the Science category: local speech-to-text server and MCP integration using Microsoft VibeVoice-ASR. OpenAI-compatible API + MCP server for Claude Code, Cursor, OpenCode.
Install
git clone https://github.com/tjameswilliams/vibevoice-serverThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (3)
get_vibevoice_statusCheck whether the model is loaded, and which device/dtype it's using.
Parameters not published.
load_vibevoice_modelPre-load the model into memory (~60-90s). Optional — the model loads automatically on first transcription.
Parameters not published.
transcribe_audioTranscribe an audio file. Pass an absolute file path and get back the transcript.
Parameters not published.
Ask AI
Ask AI about Vibevoice Server
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.