diff --git a/README.md b/README.md index 5b03c3aeb..2a3c7a342 100644 --- a/README.md +++ b/README.md @@ -2893,6 +2893,7 @@ Translation tools and services to enable AI assistants to translate content betw ### 🎙️ Speech-to-Text - [eviscerations/whisper-windows-mcp](https://github.com/eviscerations/whisper-windows-mcp) [![eviscerations/whisper-windows-mcp MCP server](https://glama.ai/mcp/servers/eviscerations/whisper-windows-mcp/badges/score.svg)](https://glama.ai/mcp/servers/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. +- [pepys/pepys-mcp](https://pepys.co/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](https://github.com/spokenmd/spoken) [![spokenmd/spoken MCP server](https://glama.ai/mcp/servers/spokenmd/spoken/badges/score.svg)](https://glama.ai/mcp/servers/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. ### 🎧 Text-to-Speech