Deepgram
Transcribe audio and video to text with Deepgram AI. Fast, accurate speech-to-text in 30+ languages.
🔑 Setup Required — Bring Your Own Key
This integration requires API credentials. Store them once via
setup_integration or the Dashboard Vault — they're encrypted
with AES-256-GCM and never exposed.
Required Credentials
deepgram_api_key
API Key
API key from console.deepgram.com → Settings → API Keys.
Get your API key at deepgram.com →
Endpoints (2)
POST
transcribe-url
Transcribe audio from a URL. Supports MP3, WAV, M4A, MP4, and more. Returns full transcript with timestamps.
| Field | Type | Required | Description |
|---|---|---|---|
url |
string | ✓ Yes | Public URL of the audio/video file to transcribe. |
language |
string | No | Language code: "en", "nl", "de", "fr", "es", "ja", etc. Default: auto-detect. |
GET
list-models
List available Deepgram models. Returns model names, languages, and capabilities.
No input parameters required.
MCP Tool Names
When using this integration through an AI assistant (Claude, ChatGPT, Cursor, etc.), the endpoints are available as MCP tools:
| Endpoint | MCP Tool Name |
|---|---|
| transcribe-url | deepgram_transcribe_url |
| list-models | deepgram_list_models |