# Deepgram — how to use (mcp.ai)

Connect your Deepgram account and use 8 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Deepgram provides AI-powered speech recognition and understanding services, offering APIs for real-time and pre-recorded audio transcription, text-to-speech, and audio intelligence.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_deepgram?ms=1787293380000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `deepgram_get_model`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/deepgram`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/deepgram/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/deepgram/get/model` — Retrieve metadata for a specific Deepgram model by its UUID. Returns detailed model information including name, architecture, supported languages, version, and capabilities. Works for both STT (speech
  - body: { model_id: string }
- `POST https://api.mcp.ai/api/deepgram/get/models` — Retrieve metadata on all public Deepgram models (speech-to-text and text-to-speech). Returns comprehensive model information including supported languages, architectures, versions, and capabilities. S
  - body: { include_outdated?: boolean }
- `POST https://api.mcp.ai/api/deepgram/get/project/usage/summary` — Retrieves aggregated usage statistics for a Deepgram project including total audio duration, billable duration, number of requests, channels processed, and confidence/relevance scores. Returns both ov
  - body: { end?: string, tag?: string, model?: string, start?: string, project_id: string, accessor_id?: string }
- `POST https://api.mcp.ai/api/deepgram/get/projects` — Tool to list all Deepgram projects. Use after authenticating with your API key.
- `POST https://api.mcp.ai/api/deepgram/list/project/scopes` — Tool to list all scopes for a specified Deepgram project. Use when you need to retrieve all permission scopes for a project.
  - body: { project_id: string }
- `POST https://api.mcp.ai/api/deepgram/list/think/models` — Tool to list available think models for AI agent processing and voice agent configuration. Use when you need to see which think models are available for voice agents.
- `POST https://api.mcp.ai/api/deepgram/speech/to/text/pre/recorded` — Tool to transcribe pre-recorded audio files into text. Use when converting a publicly accessible audio file URL to text. Primary transcript is at `results.channels[0].alternatives[0].transcript` in th
  - body: { tier?: string, model?: string, diarize?: boolean, keyterm?: string[], version?: string, keywords?: string[], language?: string, audio_url: string, punctuate?: boolean, alternatives?: integer, content_type: string, smart_format?: boolean, detect_language?: boolean, interim_results?: boolean }
- `POST https://api.mcp.ai/api/deepgram/text/to/speech/rest` — Tool to convert text into natural-sounding speech. Use when you need TTS audio from text inputs.
  - body: { text: string, model?: string, pitch?: number, speed?: number, voice?: string, version?: string, encoding?: string, language?: string, container?: string, sample_rate?: integer }

## Example prompts
- "What can I do in Deepgram?"
- "Show me a summary of my Deepgram account"

## More
- Page: https://mcp.ai/deepgram
- Agent spec (llms.txt): https://mcp.ai/deepgram/llms.txt
- Postman collection: https://mcp.ai/deepgram/postman.json