Speech-to-Text MCP Servers
3 Model Context Protocol servers in the Speech-to-Text category.
3 of 3 shown
eviscerations/whisper-windows-mcp
github.comWindows-native local audio and video transcription using whisper.cpp with Vulkan GPU acceleration. No cloud APIs, no Python. Batch processing, multilingual support, model management, and background job handling built in.
ankurmans/pepys-mcp
github.comPay-once transcription for audio, video, and whole podcast feeds via Pepys. Transcribe a file or a pasted YouTube/podcast link, get speaker diarization, export SRT/VTT, search a transcript, and check credit balance. Hosted connector (OAuth, no API key) or npx pepys-mcp. 99+ languages.
spokenmd/spoken
github.comFetch published podcast transcripts as clean Markdown with real speaker names (not "Speaker 1") via the Spoken API. Search episodes, get transcripts, check credit balance.
Attribution
Data sourced from punkpeye/awesome-mcp-servers (MIT). Synced every 24 hours.