openclaw/docs/providers/deepgram.md

summary, read_when, title

summary	read_when	title
Deepgram transcription for inbound voice notes	You want Deepgram speech-to-text for audio attachments You need a quick Deepgram config example	Deepgram

Deepgram (Audio Transcription)

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

When enabled, OpenClaw 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.

Detail	Value
Website	deepgram.com
Docs	developers.deepgram.com
Auth	DEEPGRAM_API_KEY
Default model	nova-3

Getting started

Add your Deepgram API key to the environment:

```
DEEPGRAM_API_KEY=dg_...
```

```json5 { tools: { media: { audio: { enabled: true, models: [{ provider: "deepgram", model: "nova-3" }], }, }, }, } ``` Send an audio message through any connected channel. OpenClaw transcribes it via Deepgram and injects the transcript into the reply pipeline.

Configuration options

Option	Path	Description
model	tools.media.audio.models[].model	Deepgram model id (default: nova-3)
language	tools.media.audio.models[].language	Language hint (optional)
detect_language	tools.media.audio.providerOptions.deepgram.detect_language	Enable language detection (optional)
punctuate	tools.media.audio.providerOptions.deepgram.punctuate	Enable punctuation (optional)
smart_format	tools.media.audio.providerOptions.deepgram.smart_format	Enable smart formatting (optional)

```json5 { tools: { media: { audio: { enabled: true, models: [{ provider: "deepgram", model: "nova-3", language: "en" }], }, }, }, } ``` ```json5 { 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). Deepgram transcription is **pre-recorded only** (not real-time streaming). OpenClaw uploads the complete audio file and waits for the full transcript before injecting it into the conversation.

Related

Audio, image, and video processing pipeline overview. Full config reference including media tool settings. Common issues and debugging steps. Frequently asked questions about OpenClaw setup.