vocce transcribe
io.github.cmoonagentPublished by GitHub account cmoonagentv1.1.0Updated Oct 24, 2026
Agent media tools: transcribe, summarize, notes, flashcards, doc Q&A, PDF compress. No API key.
The publisher's own server: Transcribe
Overview
A local MCP server that lets an assistant transcribe audio and video, summarize, make notes and flashcards, answer questions about documents, and compress PDFs.
- What you can do
- Transcribe local audio or video into text with SRT and VTT subtitles in many languages, or read text, markdown and subtitle files directly as input for the other tools. Summarize a recording or text into meeting minutes, lecture notes, to-dos or chapters. Generate structured study notes in outline, Cornell or key-points form. Create grounded question-and-answer flashcards from a recording or text. Answer questions about a file using only the source content, with verbatim citations. Compress a local PDF at light, balanced or strong settings while keeping text crisp.
- When to use it
- Useful when you want an assistant to turn meeting recordings, lectures or interviews into transcripts, summaries, notes or flashcards, to ask questions about a document with citations, or to shrink a PDF for email without running any model locally.
- Requirements
- Runs as a local process started with npx, so Node.js is needed; no install step and no API key. It sends files to vocce's hosted backend, so network access is required. Optional environment variables VOCCE_API_BASE and VOCCE_EDGE_BASE override the default backend endpoints. Desktop MCP clients only.
Installation
In SourceWeft
- Open vocce transcribe in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.
Other MCP clients
Follow the launch instructions in the repository.
README
vocce media — MCP server
Transcribe, summarize, take notes, make flashcards, ask questions, and compress PDFs — straight from your AI agent. Powered by vocce's hosted backend (Whisper large-v3 + LLM tools).
✨ No API key · ☁️ Hosted (no model, no GPU to run) · 🆓 Free preview
Install
Add this to your MCP client config (Claude Desktop, Cursor, Windsurf, …). There's no install step — npx fetches it on first run:
Restart your client and six tools are ready.
Tools
For the content tools, pass either file_path (media is transcribed automatically first;
.txt/.md/.srt/.vtt are read directly) or raw text.
Example prompts:
"Transcribe
~/Downloads/interview.mp4and pull out the action items." "Make 15 flashcards from~/lectures/biology-week3.mp3." "Ask~/meetings/standup.mp4: what did we decide about the launch date?" "Compress~/Documents/report.pdfto email size."
Configuration
How it works
This server is a thin client: it uploads your file to vocce's hosted backend, polls until the job is done, and hands back the result. Heavy lifting runs on vocce's GPUs — you don't download or run a model locally.
Links
- Website — https://vocce.io
- Source — https://github.com/cmoonagent/vocce-agent
- Issues — https://github.com/cmoonagent/vocce-agent/issues
License
MIT
Source: transcribe-mcp-server/README.md at commit 633f7cc
Tools
0Version history
1- v1.1.0LatestSep 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Transcribe integrations
Transcribe
so.transcribeOfficial publisher
Transcribe lets an assistant turn audio and video into speaker-labelled transcripts, subtitles, clips, and cited Q&A through a hosted remote endpoint.
Verbatim Transcribe
Published by GitHub account xyzxinlu-max
Lets an assistant drive a local Verbatim service to transcribe audio and video, poll jobs, and search a transcript library.
OpenTranscribe MCP
Published by GitHub account fbossiere
OpenTranscribe routes audio files or HTTPS URLs to a chosen speech-to-text provider and returns one normalized transcript schema over MCP.
Whisper Transcribe
Published by GitHub account ZahiriNatZuke
Lets an assistant transcribe audio files locally with faster-whisper or through the OpenAI Whisper API.
Transcribe Mcp
Published by GitHub account Soboljem
Local MCP server that transcribes audio and video, finds dead air, and converts web pages to markdown, paid per call in USDC from your own wallet.