Discussions

Hello,

We are currently using the HeyGen streaming avatar and sending text strings for the avatar to speak, which works well. However, for our new use case, we want to stream audio data instead of text—and have the avatar lip-sync to the audio in real-time.

Does HeyGen support streaming audio input directly to the avatar for lip-sync, instead of generating speech from text?
If so, could you please provide documentation or guidance on how to implement this?

Thank you!