LiveKit Community

how to set Deepgram Nova 3 multi stt in streaming mode or is it streaming by default

Thanks for reaching out, Harsh. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.


I'm happy to help you with Deepgram Nova 3 STT! When you integrate it with LiveKit, it naturally works in streaming mode by default. To get started, you just need to create an instance of the `STT` class with the model parameter set to `"nova-3"`, and then call the `stream()` method. There's no need to worry about extra setup for streaming since it's already enabled for you. If you have any more questions or need further assistance, feel free to ask!
 Sources: <https://github.com/livekit/agents/blob/f2fb5705c865ee7f220f60b5baeaf4c716db4cf6/examples/voice_agents/langgraph_agent.py#L1-L71|examples/voice_agents/langgraph_agent.py> | <https://blog.livekit.io/open-source-realtime-multimodal-ai/#/portal/signup|An open source stack for real-time multimodal AI> | <https://github.com/livekit/agents-js/blob/95ff351cad582443d8163d9487377d48842db8f7/agents/src/voice/agent.ts#L1-L65|agents/src/voice/agent.ts>