Yes, you can use OpenAI audio models with LiveKit. The OpenAI plugin for LiveKit supports text-to-speech (TTS), speech-to-text (STT), and large language models (LLM) using OpenAI's Realtime API. This allows you to create conversational, multi-modal voice agents that can process audio inputs and generate audio outputs. For more details, you can refer to the
OpenAI plugin documentation.
Would you like more detail on how to integrate these models into your application?
Sources:
-
OpenAI plugin documentation 👍 0 button 👎 1 button 💡
Hint: Mention
@millions-hair-24956 in the thread for followups.