Deepgram (Audio Transcription)

Deepgram is a speech-to-text API. In Edwin it is used for inbound audio/voice note transcription via tools.media.audio.

When enabled, Edwin uploads the audio file to Deepgram and injects the transcript into the reply pipeline ({<!-- -->{Transcript}<!-- -->} + [Audio] block). This is not streaming; it uses the pre-recorded transcription endpoint.

Website: https://deepgram.com
Docs: https://developers.deepgram.com

Quick start

1. Set your API key:

DEEPGRAM_API_KEY=dg_...

2. Enable the provider:

{
  tools: {
    media: {
      audio: {
        enabled: true,
        models: [{ provider: "deepgram", model: "nova-3" }],
      },
    },
  },
}

Options

• model: Deepgram model id (default: nova-3)
• language: language hint (optional)
• tools.media.audio.providerOptions.deepgram.detect_language: enable language detection (optional)
• tools.media.audio.providerOptions.deepgram.punctuate: enable punctuation (optional)
• tools.media.audio.providerOptions.deepgram.smart_format: enable smart formatting (optional)

Example with language:

{
  tools: {
    media: {
      audio: {
        enabled: true,
        models: [{ provider: "deepgram", model: "nova-3", language: "en" }],
      },
    },
  },
}

Example with Deepgram options:

{
  tools: {
    media: {
      audio: {
        enabled: true,
        providerOptions: {
          deepgram: {
            detect_language: true,
            punctuate: true,
            smart_format: true,
          },
        },
        models: [{ provider: "deepgram", model: "nova-3" }],
      },
    },
  },
}

Notes

• Authentication follows the standard provider auth order; DEEPGRAM_API_KEY is the simplest path.
• Override endpoints or headers with tools.media.audio.baseUrl and tools.media.audio.headers when using a proxy.
• Output follows the same audio rules as other providers (size caps, timeouts, transcript injection).