> ## Documentation Index
> Fetch the complete documentation index at: https://veryfront.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Deepgram

> Transcribe prerecorded audio from URLs and manage projects, balances, and models via the Deepgram API

## At a glance

* **Availability**: Experimental ([how to enable](/cloud/integrations)).
* **Auth**: API key.
* **Connection**: The key comes from `DEEPGRAM_API_KEY`.
* **Docs**: [https://developers.deepgram.com/reference/deepgram-api-overview](https://developers.deepgram.com/reference/deepgram-api-overview)

## Credentials

Set these per environment. See [Connect an integration](/cloud/integrations).

| Variable           | Required | Description                                                                                                         |
| ------------------ | -------- | ------------------------------------------------------------------------------------------------------------------- |
| `DEEPGRAM_API_KEY` | Yes      | Deepgram API key from the Deepgram console [Docs](https://developers.deepgram.com/docs/create-additional-api-keys). |

## Setup

1. **Create a Deepgram account**: Go to [https://console.deepgram.com](https://console.deepgram.com) and sign up. New accounts receive free credits to test transcription without a credit card.
2. **Create an API key**: In the console, open your project, go to Settings → API Keys, and create a new key. Choose the Member role (or narrower) for day-to-day transcription.
3. **Store the key**: Copy the key and add it to your .env file as DEEPGRAM\_API\_KEY=...
4. **Verify access**: Run the List Projects tool to confirm the key works, then transcribe a sample file such as [https://dpgr.am/spacewalk.wav](https://dpgr.am/spacewalk.wav)

* Authentication uses the Authorization header with the Token prefix (Authorization: Token \<key>), not Bearer
* Transcription is billed per minute of audio and draws down project credits
* The Transcribe URL tool only handles remote files - uploading raw audio bytes is not supported by this connector

Provider API reference: [https://developers.deepgram.com/reference/deepgram-api-overview](https://developers.deepgram.com/reference/deepgram-api-overview)

## Tools

| Tool                 | Access | Description                                                        |
| -------------------- | ------ | ------------------------------------------------------------------ |
| Transcribe URL       | Write  | Transcribe a prerecorded audio file from a publicly accessible URL |
| List Projects        | Read   | List the Deepgram projects associated with the API key             |
| Get Project Balances | Read   | Get the outstanding credit balances for a project                  |
| List Models          | Read   | List the speech-to-text and text-to-speech models Deepgram offers  |

## Example prompts

* Transcribe this audio file with Deepgram and give me a clean transcript: \<paste URL>
* List my Deepgram projects and check the remaining credit balance on each.