# vocce transcribe [Health: Active]

**Category:** 🎙️ Speech-to-Text  
**Repository:** https://github.com/cmoonagent/vocce-agent  
**GitHub Stars:** 0  
**Views:** 0  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/vocce-transcribe

## Description
Transcribe audio/video to text + SRT/VTT via vocce's hosted Whisper. No API key required.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "vocce-transcribe": {
    "command": "npx",
    "args": ["-y","vocce-transcribe-mcp"]
  }
}
```

## Documentation & README

# 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, …
```json
{ "mcpServers": { "vocce": { "command": "npx", "args": ["-y", "vocce-transcribe-mcp"] } } }
```
Details → [`transcribe-mcp-server/`](https://github.com/cmoonagent/vocce-agent/blob/HEAD/transcribe-mcp-server)

### 2. CLI — Python, stdlib only
```bash
python3 transcribe-cli/transcribe.py meeting.mp3 --format srt
```
Details → [`transcribe-cli/`](https://github.com/cmoonagent/vocce-agent/blob/HEAD/transcribe-cli)

### 3. Agent Skill — drop-in for Claude
See → [`agent-transcription-skill/`](https://github.com/cmoonagent/vocce-agent/blob/HEAD/agent-transcription-skill)

## Also in here
- **GitHub Action** — transcribe in CI → [`github-action/`](https://github.com/cmoonagent/vocce-agent/blob/HEAD/github-action)
- **n8n community node** — `n8n-nodes-vocce` → [`n8n-nodes-vocce/`](https://github.com/cmoonagent/vocce-agent/blob/HEAD/n8n-nodes-vocce)
- **Function calling** (OpenAI / Anthropic) + **ChatGPT Action** → [`integrations/`](https://github.com/cmoonagent/vocce-agent/blob/HEAD/integrations)
- **Directory submission kits** (MCP + Skill) → [`distribution/`](https://github.com/cmoonagent/vocce-agent/blob/HEAD/distribution)
- **MCP registry manifest** → [`server.json`](https://github.com/cmoonagent/vocce-agent/blob/HEAD/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