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.
Example client config (verify package name in the repo README)
{
"mcpServers": {
"spoken": {
"command": "npx",
"args": ["-y", "spoken"]
}
}
}Transparent heuristic — same formula for every entry. Total 57/100.
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.
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.