agents
agents copied to clipboard
How can I continue processing audio while returning it using MultimodalAgent/Openai realtime api
For example, voice conversion
Hey, can you provide more details? Are you looking into getting the audio data from the Realtime API?
@theomonnom Yes, I want to do some audio processing before returning the audio stream to the user and then return the processed audio result to the user
#953 I have submitted a PR