Skip to main content

Deepgram

Connects to the Deepgram speech-to-text API. An agent can transcribe audio from a public URL, optionally with speaker diarization.

Add to an agent node's tools array with _node_type: "tool-deepgram". See Connector Reference — How connectors are used.

Authentication

FieldRequiredDescription
api_keyYes (or deepgram_api_key)Deepgram API key, sent as Authorization: Token <api_key>.
deepgram_api_keyYes (if api_key not set)Used if api_key is not set.
{
"name": "deepgram",
"_node_type": "tool-deepgram",
"api_key": "{{ secret.DEEPGRAM_API_KEY }}"
}

Tools

deepgram_transcribe_url

Transcribe audio from a URL using Deepgram Nova-2. Faster and cheaper than uploading.

Parameters

ParameterTypeRequiredDescription
audio_urlstringYesPublic URL to audio file (mp3, mp4, wav, m4a, etc.)
modelstringNonova-2 (default) | nova | enhanced | base
languagestringNoBCP-47 language code, e.g. en-US (auto-detect when empty)
diarizebooleanNoEnable speaker diarization (labels speaker 0, 1, 2...)
punctuatebooleanNoAdd punctuation (default true)

Returns: JSON with text (full transcript), words (array of {word, start, end, confidence, speaker?}), confidence, duration, and provider ("deepgram").

Next