Use this file to discover all available pages before exploring further.

Deepgram

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

text

tools.media.audio

and for Voice Call streaming STT through

text

plugins.entries.voice-call.config.streaming

For batch transcription, OpenClaw uploads the complete audio file to Deepgram and injects the transcript into the reply pipeline (

text

{{Transcript}}

text

[Audio]

block). For Voice Call streaming, OpenClaw forwards live G.711 u-law frames over Deepgram's WebSocket

text

listen

endpoint and emits partial or final transcripts as Deepgram returns them.

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

Getting started

Set your API key

Add your Deepgram API key to the environment:


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

Enable the audio provider

```json5} { tools: { media: { audio: { enabled: true, models: [{ provider: "deepgram", model: "nova-3" }], }, }, }, } ```

Send a voice note

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
text `model`	text `tools.media.audio.models[].model`	Deepgram model id (default: text `nova-3` )
text `language`	text `tools.media.audio.models[].language`	Language hint (optional)
text `detect_language`	text `tools.media.audio.providerOptions.deepgram.detect_language`	Enable language detection (optional)
text `punctuate`	text `tools.media.audio.providerOptions.deepgram.punctuate`	Enable punctuation (optional)
text `smart_format`	text `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" }], }, }, }, } ```

Voice Call streaming STT

The bundled

text

deepgram

plugin also registers a realtime transcription provider for the Voice Call plugin.

Setting	Config path	Default
API key	text `plugins.entries.voice-call.config.streaming.providers.deepgram.apiKey`	Falls back to text `DEEPGRAM_API_KEY`
Model	text `...deepgram.model`	text `nova-3`
Language	text `...deepgram.language`	(unset)
Encoding	text `...deepgram.encoding`	text `mulaw`
Sample rate	text `...deepgram.sampleRate`	text `8000`
Endpointing	text `...deepgram.endpointingMs`	text `800`
Interim results	text `...deepgram.interimResults`	text `true`


json5
{
  plugins: {
    entries: {
      "voice-call": {
        config: {
          streaming: {
            enabled: true,
            provider: "deepgram",
            providers: {
              deepgram: {
                apiKey: "${DEEPGRAM_API_KEY}",
                model: "nova-3",
                endpointingMs: 800,
                language: "en-US",
              },
            },
          },
        },
      },
    },
  },
}

note

Voice Call receives telephony audio as 8 kHz G.711 u-law. The Deepgram streaming provider defaults to `encoding: "mulaw"` and `sampleRate: 8000`, so Twilio media frames can be forwarded directly.

Notes

Media tools

Audio, image, and video processing pipeline overview.

Configuration

Full config reference including media tool settings.

Troubleshooting

Common issues and debugging steps.

FAQ

Frequently asked questions about OpenClaw setup.

OpenClaw Docs

Deepgram

Getting started

Set your API key

Enable the audio provider

Send a voice note

Configuration options

Voice Call streaming STT

note

Notes

Related

Media tools

Configuration

Troubleshooting

FAQ