Skip to main content

Nova-3 Pharma: Speech-to-Text for Pharmaceutical Use Cases (English)

By Steven Van ·

The Nova-3 model targets accurate drug-name recognition for pharmacy and healthcare voice agents, in English batch and streaming.

Deepgram has released nova-3-pharma, a Nova-3 speech-to-text model built for pharmaceutical vocabulary, with a focus on accurate drug-name recognition. It's aimed at pharmacy and healthcare voice-agent workflows where getting the medication name right matters most.

The model is available now through the API by setting model=nova-3-pharma, for both pre-recorded and real-time streaming transcription. It supports English, including en-US, en-AU, en-CA, en-GB, en-IE, en-IN, and en-NZ. It's available to hosted customers directly; self-hosted customers need to request it from their Deepgram account representative. More details are in the Models & Languages Overview.

Deepgram
Deepgram
Power enterprise voice solutions with Deepgram’s Speech-to-Text, Text-to-Speech, and Voice Agent APIs. Real-time, accurate, and built for scale.
View Deepgram →

Read the original announcement →

Read Nova-3 Pharma: Speech-to-Text for Pharmaceutical Use Cases (English) on Creators Toolbox