Deepgram Nova-3 Stream | EmpirioLabs AI Docs

Deepgram · Transcription

WEBSOCKET /v1/realtime

Live transcription over a socket, returning interim results while the speaker is still talking and a settled transcript once each phrase ends.

At a glance

Field	Value
Model id	`deepgram-nova-3-stream`
Model release date	-
Input modalities	Audio
Output modalities	Text
Context window	-
Weight precision	-
Features	transcription, speech_to_text, realtime, streaming_asr, multilingual
Native inference	No
New	Yes
Supported endpoints	`WEBSOCKET /v1/realtime`
Alternate model ids	`nova-3-stream`, `deepgram/deepgram-nova-3-stream`

Pricing

Charge	Spec	Rate
Transcription	per minute of audio	$0.025

Example request

curl https://api.empiriolabs.ai/v1/audio/transcriptions \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -F model=deepgram-nova-3-stream \
  -F file=@meeting.mp3

Parameters

This model accepts the standard chat completion parameters (see the API reference).

Notes

Live transcription over a WebSocket at wss://api.empiriolabs.ai/v1/realtime?model=deepgram-nova-3-stream, authenticated with the ordinary Authorization Bearer header. Send 16 kHz mono 16-bit PCM as binary frames and read transcript events back; interim results arrive while the speaker is still talking, and each phrase settles with is_final. Add language= to the connection URL to transcribe a specific language. Billing is per minute of the audio you send up.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/deepgram-nova-3-stream.