Issue with Deepgram JS SDK: TTS speak.live Failing

[renjithraj2005]

I am trying to implement Text-to-Speech (TTS) using the Deepgram JS SDK in my project. Here’s the code snippet I am using:

const deepgram = createClient(DEEPGRAM_API_KEY);
const dgConnection = deepgram.speak.live({
  model: "aura-asteria-en",
  encoding: 'linear16',
  sample_rate: 48000,
});

When I run this code, the connection to the WebSocket fails, and I get an error with the following URL:

wss://api.deepgram.com/v1/speak?model=aura-asteria-en&encoding=linear16&sample_rate=48000
It seems the connection is not being established, and I’m not sure what is causing the issue.

Steps to Reproduce:

Use the Deepgram JS SDK.
Configure the speak.live method with the parameters shown above.
Attempt to establish a WebSocket connection.

[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?

• A request ID that triggered your error or issue.

[renjithraj2005]

I got this information from the log. Any pointers to resolve the issue ?

[jpvajda]

In this screen shot it looks like you are requesting a model with a value of aura-asteria-e not aura-asteria-enbased on the URL I am seeing. This might be an issue with UI's rendering of that URL, but you might want to check to ensure you are passing the model value to our API correctly.

Also if you can provide the request ID as text I can look that up in our logs, it's hard to extract that out of the image.

One way to check your access to a model is to use our Get Projects Models endpoint

https://developers.deepgram.com/reference/get-project-models

You should have access to all Aura Models, but this would be worth double checking.