vocce transcribe MCP server
io.github.cmoonagent/vocce-agent·v1.1.0Agent media tools: transcribe, summarize, notes, flashcards, doc Q&A, PDF compress. No API key.
0 stars47 downloads/wk
Reviews
Write oneNobody has reviewed vocce transcribe yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
vocce transcribe tools (6)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
ask_documentAsk a question about a recording or document. Answers only from the source, with verbatim citations; says so if the answer isn't in the file.
compress_pdfCompress a local PDF file (images re-encoded, text stays crisp). Levels: light, balanced, strong. Writes the result next to the input (or to output_path) and returns both sizes.
generate_flashcardsGenerate study flashcards (question/answer pairs) from a recording or text. Every card is grounded in the source.
generate_notesTurn a recording or text into structured study notes (markdown). Styles: outline, cornell, key-points.
summarizeSummarize a recording or text into meeting minutes, lecture notes, a to-do list, or chapters.
transcribeTranscribe a local audio or video file to text and subtitles using vocce's hosted Whisper large-v3. Returns plain text, SRT, and VTT.
Public scan report
scanner v0.1.9 · 2026-09-25 · same rubric, same numbers if you re-run it
- Code scan2 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitylocal package, no credentials required12/15
- Maintenancelast push 70 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How vocce transcribe compares
Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 88/100
- higher than 80% of 4,460 AI and agents servers
- Tools
- 6
- the typical AI and agents server has 6
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- Downloads a week
- 47
- more than 39% of 1,538 AI and agents servers with a package
What its tools let an agent do: 4 read · 2 create
Install vocce transcribe in Claude Code, Cursor or VS Code
Runs npx -y vocce-transcribe-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add vocce-agent -- npx -y vocce-transcribe-mcp
What the publisher says
From the vocce transcribe repository's README, as published. We do not edit it. Read it on GitHub
vocce — agent integrations
Hosted audio/video transcription for AI agents and automations. No API key. No local model. Upload a file, get back text + SRT + VTT + timestamped segments — powered by Whisper large-v3 on vocce's GPU.
→ Product: https://vocce.io · API docs: https://vocce.io/api · OpenAPI: https://vocce.io/openapi.json
Three ways to use it
1. MCP server — for Claude, Cursor, Windsurf, …
{ "mcpServers": { "vocce": { "command": "npx", "args": ["-y", "vocce-transcribe-mcp"] } } }Details → transcribe-mcp-server/
2. CLI — Python, stdlib only
python3 transcribe-cli/transcribe.py meeting.mp3 --format srtDetails → transcribe-cli/
3. Agent Skill — drop-in for Claude
See → agent-transcription-skill/
Also in here
- GitHub Action — transcribe in CI → github-action/
- n8n community node — n8n-nodes-vocce → n8n-nodes-vocce/
- Function calling (OpenAI / Anthropic) + ChatGPT Action → integrations/
- Directory submission kits (MCP + Skill) → distribution/
- MCP registry manifest → server.json
How it works
Every package is a thin client: it uploads your file to vocce's hosted backend, polls until the job is done, and returns the result. The transcription runs on vocce's GPU — nothing to install, no model to download. The backend is the product; these clients are open source (MIT).
License
MIT
Nothing above is checked by us. What we check is on the safety report.
vocce transcribe: common questions
- Is vocce transcribe MCP server safe?
- Yes, by our scan: it is graded A (88/100). Read the vocce transcribe safety report
- How do I install vocce transcribe?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does vocce transcribe need an API key?
- No secret keys are declared. It reads 1 setting from the environment.
- Is vocce transcribe maintained?
- The last commit was 109 days ago (2026-07-18). The latest release is v1.1.0.
- What can I use instead of vocce transcribe?
- Servers from other publishers that do the same job: Agent-Native Clips MCP server, IWE (iwe.md) MCP server and SuperCompress MCP server.
- How does vocce transcribe compare with other AI and agents MCP servers?
- safety score 88/100 (higher than 80% of 4,460 AI and agents servers); tools 6 (the typical AI and agents server has 6); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to vocce transcribe
Same job from other publishers: the closest match first, then the best rated.
- Agent-Native ClipsScreen recording, meeting notes, and voice dictation - all with AInot reviewedEstablishedA
- IWE (iwe.md)Markdown knowledge base as agent memory. Runs against the notes directory it is started in.not reviewedEstablishedA
- SuperCompressCompress coding-agent context ~64%. Hosted Neural Keep MCP for Cursor/Claude/Codex.not reviewedEstablishedB
- SpotifyscraperPublic Spotify metadata, lyrics and podcasts for LLM agents. No API key, read-only.not reviewedEstablishedB
- Mnemoverse MemoryHosted agent memory that learns from outcomes, with shared rooms. No key: mcp.mnemoverse.com/mcpnot reviewedEstablishedA