Home › MCP servers › Speech-to-Text

Speech-to-Text – MCP servers

3 MCP servers in the category Speech-to-Text. Open-source Model Context Protocol (MCP) servers that let AI assistants and agents use external tools and data. Entries come from the community list awesome-mcp-servers; we have not tested each server, so check the repository before you install one.

ankurmans/pepys-mcp

Transcribe audio, video, YouTube links and podcast feeds via Pepys, with speaker diarization, SRT/VTT export and transcript search.

eviscerations/whisper-windows-mcp

Local audio and video transcription on Windows using whisper.cpp with Vulkan GPU acceleration: batch processing, multilingual support and background…

spokenmd/spoken

Search podcast episodes and fetch published transcripts as Markdown with real speaker names via the Spoken API.