Providers and ModelsDeepgram

Deepgram-Nova-3

Deepgram-Nova-3

Provider: Deepgram
Category: Transcription
Endpoint: POST /v1/audio/transcriptions
Context window: —
Served from: —

Speech-to-text transcription using the Nova-3 model with multi-language support and advanced customizable settings for production workloads.

At a glance

FieldValue
Model iddeepgram-nova-3
Input modalitiesaudio
Output modalitiestext
Context window—
Region—
Featurestranscription, speech_to_text
NewNo
Native inferenceNo

Pricing

ChargeSpecRate
Transcriptionper minute of audio$0.014

Example request

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

Parameters

ParameterTypeRequiredDefaultDescription
filestringyes—Audio file (multipart upload) OR file_url for the JSON path
file_urlstringno—Public URL to fetch audio from
languagestringno—Optional ISO-639-1 code; auto-detected if omitted
model_variantstringno"nova-3"Provider-specific model name
smart_formatbooleannotrue—
punctuatebooleannotrue—
diarizebooleannofalse—

Live machine-readable schema is also available at GET https://api.empiriolabs.ai/v1/models/deepgram-nova-3.