Platform edition
Deepgram for Windows
Deepgram Nova-3 and Nova-2 cloud transcription with live text while recording.
- Version
- 1.1.3
- Plugin ID
- com.
typewhisper. deepgram - Requirements
- TypeWhisper 1.1.0 or newer · Windows 10 or newer · A Deepgram API key
Inside this edition
Features in this edition
- Cloud transcription with Deepgram Nova-3 or Nova-2
- Live text while recording through Deepgram streaming
- Automatic language detection or a fixed language from the selected model's language list
- Smart formatting and punctuation for live and recorded audio
- Check connection verifies the API key without uploading audio
Settings in this edition
- Enter your Deepgram API key under API key, choose Save settings, and verify it with Check connection
- Choose Nova-3 or Nova-2 under Transcription model and, if it appears, choose Use selected model
Guide for this edition
Set up the add-on and verify its platform-specific capabilities with a first practical workflow.
Roles in TypeWhisper
Setup
- In TypeWhisper, open Settings > Discover plugins and install Deepgram. The add-on then appears in the Settings sidebar, and its page opens. If it is already installed, open its page in the sidebar.
- On the add-on's page, review the options available in this edition.
- Enter your Deepgram API key under API key, choose Save settings, and verify it with Check connection
- Choose Nova-3 or Nova-2 under Transcription model and, if it appears, choose Use selected model
- Under Settings > Dictation, select Deepgram as the Provider and choose a Model. A Dictation Only workflow can also use its own transcription model.
In practice
- Transcription
- Dictate a few sentences with Deepgram and check the language, model, and result before you use it for longer recordings.