Help with Building a Use Case and MVP for Deepgram’s Medical Model

[formai-solutions]

Hi everyone, I’m Robert!

I’m working on demonstrating Deepgram’s Nova-2 Medical model for Pro-Med Grupo Mexico. The focus is on using real-time transcription to enhance clinical documentation. However, I’m not a coder, and I’m looking for guidance on how to start building a minimum viable product (MVP) or any use case examples that might help me get started.

Any advice or resources would be much appreciated!

Thanks in advance!

[team-deepgram]

Thanks for asking your question about Deepgram! If you didn't already include it in your post, please be sure to add as much detail as possible so we can assist you efficiently, such as:

• The request_id if you have a question about your requests or transcription responses.
• The features you used or the full api.deepgram.com URL you sent your request to, including parameters.
• Any code snippets you can share.

[jkroll-deepgram]

@formai-solutions Hi Robert! One option is to reuse our demo at https://deepgram-conversational-demo.vercel.app/. That app has the voicebot talk about Deepgram. The code is open-source, so if you're able to get into some technical work, you can clone the repository, and change the system prompt here, as well as switching from Nova-2 to Nova-2 Medical here. Then you can run the edited version on your computer as a customized demo.

Another option is to log into the Deepgram Console, go to "Demo: Transcribe your voice live" near the bottom, "Start Mission", and then you can use our pre-built demo to show streaming transcription (not a voicebot). That will use our Nova-2 model.

Finally, you can upload files for pre-recorded transcription on our Playground. You can enter in model names, including nova-2-medical, to run tests on the Nova-2 Medical model. That won't be for a streaming use-case.