AI Streaming

The Stream action will connect the call to a WebSocket server and stream real-time audio data. This can be used for scenarios like real-time AI processing or interactive voice response systems.

Curl

Streaming action JSON

[
  {
    action: "stream",
    ws_url: "ws://example.tcp.ngrok.url",
    listen_mode: "both",
    voice_quality: "8000",
    stream_on_answer: true
  }
]

Parameters type and description

Parameter	Type	Description
*action	string	The PCMO action to control the flow of the call.
*ws_url	string	The WebSocket URL where the audio stream will be sent.
*listen_mode	string	Determines which part of the call audio is captured and stored Caller: The voice of the person who initiated the call will be recorded and stored. Callee: The voice of the person receiving the call will be recorded and stored. Both: the voices from both the caller and the callee will be recorded and stored.
voice_quality	string	The desired voice quality in bits per second. Options are 8000, 16000.
stream_on_answer	boolean	Whether to start streaming after the call is answered.The default value is false.

Note

The * marked parameter is mandatory.

Node.js

The stream() method in the PiopiyAction class sets up a WebSocket connection to transmit the call's audio in real time. This is ideal for scenarios such as real-time AI processing, interactive voice response (IVR) systems, or any application where live call audio needs to be analyzed or processed.

const {PiopiyAction} = require("piopiy");

const action = new PiopiyAction();

const ws_url = "ws://example.tcp.ngrok.url"

const options = { listen_mode: "caller", voice_quality: "8000", stream_on_answer: true }

action.stream( ws_url, options )

Parameters type and description

Mandatory parameters

Parameter	Type	Description
ws_url	string	The WebSocket URL provided by the ngrok TCP service.
options	object	An object containing optional parameters (listen_mode).

Options parameters

Parameter	Type	Description
listen_mode	string	Determines which part of the call audio is captured and stored Caller: The voice of the person who initiated the call will be recorded and stored. Callee: The voice of the person receiving the call will be recorded and stored. Both: the voices from both the caller and the callee will be recorded and stored.
voice_quality	string	The desired voice quality in bits per second. Options are 8000, 16000.
stream_on_answer	boolean	Whether to start streaming after the call is answered. The default value is false.

Python

The stream() method in the PiopiyAction class sets up a WebSocket connection to transmit the call's audio in real time. This is ideal for scenarios such as real-time AI processing, interactive voice response (IVR) systems, or any application where live call audio needs to be analyzed or processed.

from piopiy import  Action

action = Action()

ws_url = "ws://example.tcp.ngrok.url"

options = { listen_mode: "caller", voice_quality: "8000", stream_on_answer: true }

action.stream( ws_url, options )

Parameters type and description

Mandatory parameters

Parameter	Type	Description
ws_url	string	The WebSocket URL provided by the ngrok TCP service.
options	object	An object containing optional parameters (listen_mode).

Options parameters

Parameter	Type	Description
listen_mode	string	Determines which part of the call audio is captured and stored Caller: The voice of the person who initiated the call will be recorded and stored. Callee: The voice of the person receiving the call will be recorded and stored. Both: the voices from both the caller and the callee will be recorded and stored.
voice_quality	string	The desired voice quality in bits per second. Options are 8000, 16000.
stream_on_answer	boolean	Whether to start streaming after the call is answered.The default value is false.