# Orchard MCP Server

Speech-to-text for real-world Spanish and Portuguese, as MCP tools.

[Orchard](https://orchardrun.com) is a transcription and speaker-diarization
API built for LATAM audio: call centers, phone recordings, meetings, field
audio. This server lets any MCP-capable assistant (Claude Desktop, Claude
Code, Cursor, custom agents) transcribe audio conversationally.

## Tools

| tool | what it does |
|---|---|
| `transcribe_file` | Transcribe a local audio file. Optional speaker diarization (`diarize: true`), speaker-count hints, domain prompt. Language auto-detected. |
| `transcribe_url` | Transcribe from a YouTube link or direct audio URL. |
| `get_transcription` | Fetch a job's transcript, optionally as `srt`, `vtt`, `md` or plain text. |
| `get_usage` | Account usage summary and remaining balance. |

Long audio is handled automatically: the tool enqueues the job, polls until
it finishes and returns the final transcript in one call.

## Setup

1. Get an API key at [orchardrun.com](https://orchardrun.com) (free tier, no
   card required).
2. Add the server to your MCP client config:

```json
{
  "mcpServers": {
    "orchard": {
      "command": "npx",
      "args": ["-y", "orchard-mcp"],
      "env": { "ORCHARD_API_KEY": "ork_..." }
    }
  }
}
```

For Claude Code:

```bash
claude mcp add orchard -e ORCHARD_API_KEY=ork_... -- npx -y orchard-mcp
```

## Example prompts

- "Transcribe `/Users/me/call.mp3` and tell me who said what."
- "Transcribe this YouTube interview and summarize each speaker's position."
- "Transcribe `meeting.wav` with diarization for 3 speakers and give me the
  action items per person."
- "Get job `abc123` as SRT subtitles."

## Notes

- Language is auto-detected when omitted; pass `language: "es"` (or `pt`,
  `en`, ...) to pin it.
- `prompt` biases the transcriber toward names, brands or domain jargon.
- Set `ORCHARD_API_URL` to point at a different environment (defaults to
  `https://api.orchardrun.com`).

MIT © Orchard