---
date: "2024-03-14T18:50:37.000Z"
title: "2024-03-14"
tags: ["deepgram","vocode"]
draft: false
---

I spent some time exploring Deepgram's Next.js [starter app](https://github.com/deepgram-starters/live-nextjs-starter).
I was hoping I could use it to generate a transcription in realtime but it was more like real-time captions.
The responses from the server were sometimes corrections of previous transcriptions.
Maybe there is a way to make this a transcription but I wasn't sure.

---

I also tried out vocode's [Python library](https://docs.vocode.dev/open-source/python-quickstart) for building voice-based LLM applications.
By far the hardest part of this was getting an Azure account, which I believe is used to synthesize the LLM response as speech.
I had the demo working end to end but it was a bit sensitive to background noise [as they note](https://docs.vocode.dev/open-source/python-quickstart#a-note-on-echo-cancellation).
I haven't had a chance to play around with any configurations they provide.