Speech-to-Text
3 MCP servers and agent skills in the Speech-to-Text category, ranked by quality score — 3 results.
eviscerations/whisper-windows-mcp
Windows-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
Pay-once transcription for audio, video, and whole podcast feeds via [Pepys](https://pepys.co). 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
Fetch published podcast transcripts as clean Markdown with real speaker names (not "Speaker 1") via the [Spoken](https://spoken.md) API. Search episodes, get transcripts, check credit balance.