Skip to content

nova-3-medical

deepgram/nova-3-medical

Clinical-audio variant of Nova-3, released March 2025 for batch and streaming, which gained multilingual medical transcription in 10 languages in October 2026. Deepgram reported a 3.44% median WER at launch; nova-3-pharma covers drug terminology separately.

API
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -F 'model=deepgram/nova-3-medical' \
  -F 'file=@recording.wav'
Input Price
$0.0037 / minute
Output Price
—
Input
Audio
Output
Text

Capabilities

Explore what nova-3-medical supports, then use the API section for a request tailored to this model.

Batch

Model Information

Provider
Deepgram
Product
Speech-to-Text
Release Date
Mar 3, 2025
Data Policy
Configurable
Region
Unknown
Input
Audio
Output
Text
Provider Documentation

Playground

Try nova-3-medical by Deepgram. Requests use the selected workspace’s credits and API pricing.

nova-3-medicalCredits —
nova-3-medical
Attach an audio file to turn speech into text.

Providers

Compare available endpoints, pricing, and context limits for nova-3-medical.

ProviderContextOutputInput PriceOutput PriceEndpoint
DeepgramNot specifiedText$0.0037 / minute—
deepgram/nova-3-medical:deepgram

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max seconds3600
Formatswav, mp3, flac, m4a, ogg, webm

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

API
curl "$AUDIOLAB_API_URL/v1/audio/transcriptions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -F 'model=deepgram/nova-3-medical' \
  -F 'file=@recording.wav'
Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

ParameterDetails
modeldeepgram/nova-3-medical — Required model identifier.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max seconds3600
Formatswav, mp3, flac, m4a, ogg, webm

Similar Models

Explore more speech-to-text and compare their capabilities.

ModelContextInput PriceOutput Price
Flux MultilingualDeepgramNot specified$0.0078 / minute—
flux-general-multiDeepgramNot specified$0.0066 / minute—
FluxDeepgramNot specified$0.0065 / minute—
flux-general-enDeepgramNot specified$0.0055 / minute—
Nova-3DeepgramNot specified$0.0037 / minute—
nova-2-atcDeepgramNot specified$0.0037 / minute—
View All Speech-to-Text