What language and framework does the voice agent in the Deepgram Playground run on?

[expozeur]

Title says it all :)

[deepgram-community[bot]]

Thanks for asking your question. Please be sure to reply with as much detail as possible so the community can assist you efficiently.
_{Consider joining our Discord community for more opportunity to engage with your fellow Deepgram users. You can earn points which can be redeemed for cool stuff by being active in our communities!}

[deepgram-community[bot]]

Hey there! It looks like you haven't connected your GitHub account to your Deepgram account. You can do this at https://community.deepgram.com - being verified through this process will allow our team to help you in a much more streamlined fashion.

[deepgram-community[bot]]

It looks like we're missing some important information to help debug your issue. Would you mind providing us with the following details in a reply?

• The programming language you are working in (e.g. JavaScript, Python).
• The deepgram product you are using (e.g Speech to Text, Agent API)
• A request ID that triggered your error or issue.

[fakemonster]

Great question. The answer depends on exactly what you mean by "voice agent", but assuming it's "the actual voice chat experience", the answer is "no framework": it's implemented in vanilla typescript as two web components. One for audio & websocket management, one for the animation.

We briefly considered using Lit to simplify the implementation a bit, but at the end of the day, the bulk of the complexity is really about the MediaStream, Web Audio, WebSocket, and Canvas APIs, not web components themselves, so we figured we'd leave it vanilla and save a few KB.

[expozeur]

I am, as far as I can tell, replicating that right now but failing. I am using Claude 4 to debug, but keep running into the same conclusion that the errors are Deepgram related. This is why I was hoping to just copy the playground code. So far, with the help of AI, we've looked at all of the current frameworks Deepgram has for a starter agent on Github. But my friend Claude and I cannot figure out why the voices seem to be lessor quality than the playground. I think Zeus is best, but I cannot figure out why sometimes the responses sound like he is underwater.

And this is among other issues, like not being able to disable the filtering out of utterances, or a woman's voice chiming in when I am using Zeus.