$ loading_
Transcribe audio, video, and podcasts into speaker-labeled timed subtitles.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "co.pepys/pepys-mcp" MCP server from askskill: Run: claude mcp add 'co-pepys-pepys-mcp' -- npx -y pepys-mcp
Please transcribe this interview video, identify different speakers, and output a timed SRT plus a clean plain-text transcript.
A speaker-labeled subtitle file and a clean interview transcript for editing and quoting.
Here is a podcast episode link. Transcribe it directly, keep timestamps, and generate a VTT subtitle file.
The podcast is fetched and transcribed from the link, producing timed subtitles for publishing or search.
Please process the latest 20 episodes in this podcast feed and batch-generate transcripts, speaker diarization, and SRT files for each episode.
Batch transcription results organized by episode, including speaker separation and subtitle files for archiving and reuse.
No documentation provided
Check the source repo for usage and examples.
Transcribe audio into structured notes with speakers, timestamps, summaries, and action items.
Download YouTube videos and transcribe speech locally with Whisper.
Transcribe audio and video into searchable text with speaker diarization support.
Transcribe audio or video to text with optional speaker labeling.
Extract YouTube video transcripts for search, analysis, repurposing, and note-taking.
Fetch and transcribe YouTube subtitles for multilingual LLM analysis and chat.