# Audivo MCP server

> Transcribe podcast episodes and YouTube videos into text for AI clients using links, files, or searches.

- Repository: https://github.com/AudivoDotDev/mcp
- Page: https://hostedmcp.org/servers/audivodotdev/mcp
- Transport: stdio, remote
- Stars: 0
- License: MIT
- Latest version: 0.4.2

## Install

### Claude Code

```sh
claude mcp add --env 'AUDIVO_API_KEY=<YOUR_AUDIVO_API_KEY>' mcp -- npx -y @audivo/mcp
```

### Cursor (`~/.cursor/mcp.json`)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@audivo/mcp"
      ],
      "env": {
        "AUDIVO_API_KEY": "<YOUR_AUDIVO_API_KEY>"
      }
    }
  }
}
```

### VS Code (`.vscode/mcp.json`)

```json
{
  "servers": {
    "mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@audivo/mcp"
      ],
      "env": {
        "AUDIVO_API_KEY": "<YOUR_AUDIVO_API_KEY>"
      }
    }
  }
}
```

### VS Code CLI

```sh
code --add-mcp '{"name":"mcp","type":"stdio","command":"npx","args":["-y","@audivo/mcp"],"env":{"AUDIVO_API_KEY":"<YOUR_AUDIVO_API_KEY>"}}'
```

### Claude Desktop (`claude_desktop_config.json`)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@audivo/mcp"
      ],
      "env": {
        "AUDIVO_API_KEY": "<YOUR_AUDIVO_API_KEY>"
      }
    }
  }
}
```

### Codex

```sh
codex mcp add mcp --env 'AUDIVO_API_KEY=<YOUR_AUDIVO_API_KEY>' -- npx -y @audivo/mcp
```

### Codex config.toml (`~/.codex/config.toml`)

```toml
[mcp_servers.mcp]
command = "npx"
args = ["-y", "@audivo/mcp"]

[mcp_servers.mcp.env]
AUDIVO_API_KEY = "<YOUR_AUDIVO_API_KEY>"
```

### Gemini CLI

```sh
gemini mcp add -s user -e 'AUDIVO_API_KEY=<YOUR_AUDIVO_API_KEY>' mcp npx -- -y @audivo/mcp
```

### Gemini settings.json (`~/.gemini/settings.json`)

```json
{
  "mcpServers": {
    "mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@audivo/mcp"
      ],
      "env": {
        "AUDIVO_API_KEY": "<YOUR_AUDIVO_API_KEY>"
      }
    }
  }
}
```

## Environment variables

| Name | Required | Secret | Description |
|---|---|---|---|
| `AUDIVO_API_KEY` | yes | yes | An Audivo API key (hk_live_...) from https://dash.audivo.dev |

## Tools (13)

- `transcribe`
- `search_shows`
- `chart_shows`
- `list_episodes`
- `quote`
- `confirm`
- `group_status`
- `list_groups`
- `cancel_group`
- `read_transcript`
- `list_transcripts`
- `upload_audio`
- `youtube_search`

## FAQ

### How do I transcribe a YouTube video?

On the local server, you can use the `youtube_search` tool to find an episode and then pass its link to the `transcribe` tool.

### What are the file size and duration limits for uploads?

You can upload files from 1 byte up to 5 GiB, with a maximum duration of 10 hours.

### How does the transcription process work for long episodes?

Transcripts are returned one page at a time, with each page containing approximately 40,000 characters.
