You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
We are adding a face to Vapi's AI agent but there is a limitation:
We want to be able to receive raw PCM16 audio bytes to pass that to our facial animation model.
The text was updated successfully, but these errors were encountered:
We have a similar need actually. We are not displaying a face, but we'd also like to be able to show an animation of sorts to visualize the agent speaking.
I also found a workaround to query the DOM for audio elements that are playing live media streams through the quickstart-react webpage, then for each stream, I created an AudioContext and connect it to a ScriptProcessorNode to capture raw PCM audio samples. Note that the audio capture itself isn’t handled by an external library, it uses the browser’s native Web Audio API (with an AudioContext and ScriptProcessorNode).
We are adding a face to Vapi's AI agent but there is a limitation:
We want to be able to receive raw PCM16 audio bytes to pass that to our facial animation model.
The text was updated successfully, but these errors were encountered: