{
  "markdown": "# vocce — agent integrations\n\nHosted audio/video transcription for AI agents and automations.\n**No API key. No local model.** Upload a file, get back text + SRT + VTT + timestamped segments —\npowered by Whisper large-v3 on vocce's GPU.\n\n→ Product: https://vocce.io · API docs: https://vocce.io/api · OpenAPI: https://vocce.io/openapi.json\n\n## Three ways to use it\n\n### 1. MCP server — for Claude, Cursor, Windsurf, …\n```json\n{ \"mcpServers\": { \"vocce\": { \"command\": \"npx\", \"args\": [\"-y\", \"vocce-transcribe-mcp\"] } } }\n```\nDetails → [`transcribe-mcp-server/`](./transcribe-mcp-server)\n\n### 2. CLI — Python, stdlib only\n```bash\npython3 transcribe-cli/transcribe.py meeting.mp3 --format srt\n```\nDetails → [`transcribe-cli/`](./transcribe-cli)\n\n### 3. Agent Skill — drop-in for Claude\nSee → [`agent-transcription-skill/`](./agent-transcription-skill)\n\n## Also in here\n- **GitHub Action** — transcribe in CI → [`github-action/`](./github-action)\n- **n8n community node** — `n8n-nodes-vocce` → [`n8n-nodes-vocce/`](./n8n-nodes-vocce)\n- **Function calling** (OpenAI / Anthropic) + **ChatGPT Action** → [`integrations/`](./integrations)\n- **Directory submission kits** (MCP + Skill) → [`distribution/`](./distribution)\n- **MCP registry manifest** → [`server.json`](./server.json)\n\n## How it works\nEvery package is a thin client: it uploads your file to vocce's hosted backend, polls until the job\nis done, and returns the result. The transcription runs on vocce's GPU — nothing to install, no model\nto download. The backend is the product; these clients are open source (MIT).\n\n## License\nMIT\n",
  "bytes": 1584,
  "sha": "aca6f8c491198945186804620afcfd749e00e50e63d8fceb54b15c38edf71470",
  "repo_slug": "cmoonagent/vocce-agent",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_cmoonagent_vocce_agent_d2612ac0/readme"
}