Ezra
11/08/2024, 5:53 PMVapi
11/08/2024, 5:55 PMlistenUrl, you typically receive audio data in the form of PCM buffer. However, if you're looking to receive text-transcript data alongside the audio, you should ensure that the service you're using is configured to send both audio and transcription data over the WebSocket connection.
If the service supports it, you may need to set specific parameters or use a particular message type to indicate that you want to receive text-transcript data. Please check the documentation of the Voice API you are using to see how to enable transcription data to be sent over the WebSocket connection.
If you're already expecting to receive text-transcript data and it's not coming through, there might be an issue with the configuration or the service itself. In that case, please ask support for more info on this.Vapi
11/08/2024, 5:55 PMShubham Bajaj
11/09/2024, 2:01 AMEzra
11/09/2024, 2:17 AM