# Deepgram

> Use this tool when you need to transcribe audio or video files into text, or analyze audio data for insights, and integrate speech recognition capabilities into your application. It solves problems such as inaccurate transcription, poor audio quality, and manual data analysis, by providing a dynamic and streamlined audio intelligence solution. It accepts audio files or streams as input and outputs transcribed text, with support for stdio and SSE transports.

Canonical page: https://skillsregistry.net/skills/deepgram  
JSON: https://api.skillsregistry.net/v1/skills/deepgram

## Description

Integrates Deepgram's speech recognition and audio intelligence APIs, with a dynamic tool list fetched from the API at runtime. Supports stdio and SSE transports and is bundled with the Deepgram CLI for streamlined developer workflows.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/deepgram)
- **Repository:** <https://github.com/deepgram/mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "deepgram"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/deepgram` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/deepgram/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt