This is the type of the message. "voice-request" is sent when using assistant.voice={ \"type\": \"custom-voice\" }. Here is what the request will look like: POST https://{assistant.voice.server.url} Content-Type: application/json { "messsage": { "type": "voice-request", "text": "Hello, world!", "sampleRate": 24000, …other metadata about the call… } } The expected response is 1-channel 16-bit raw PCM audio at the sample rate specified in the request. Here is how the response will be piped to the transport: response.on('data', (chunk: Buffer) => { outputStream.write(chunk); });