spokenmd/spoken C
spokenmd/spoken
MCP Server
Active
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.
ankurmans/pepys-mcp
ankurmans/pepys-mcp
MCP Server
Maintained
MIT
cloudlocal
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.
D Quality 43/100
★ 0 stars
Updated 1mo ago
TypeScript
Installation
Example client config (verify package name in the repo README)
{
"mcpServers": {
"pepys-mcp": {
"command": "npx",
"args": ["-y", "pepys-mcp"]
}
}
}Quality score breakdown
Transparent heuristic — same formula for every entry. Total 43/100.
GitHub stars (log scale)0/40
Maintenance activity18/25
License present10/10
Official project0/10
Not archived5/5
Meaningful description5/5
Repo topics set5/5
Related in Speech-to-Text
eviscerations/whisper-windows-mcp C
eviscerations/whisper-windows-mcp
MCP Server
Active
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.