Webhooks for streaming speech-to-text

import assemblyai as aai
from assemblyai.streaming.v3 import (
    BeginEvent,
    StreamingClient,
    StreamingClientOptions,
    StreamingError,
    StreamingEvents,
    StreamingParameters,
    TerminationEvent,
    TurnEvent,
)
from typing import Type

api_key = "<YOUR_API_KEY>"

def on_begin(self: Type[StreamingClient], event: BeginEvent):
    print(f"Session started: {event}")
    print("Connected. Speak into your microphone; press Ctrl+C to stop.")

def on_turn(self: Type[StreamingClient], event: TurnEvent):
    print(f"{event.transcript} ({event.end_of_turn})")

def on_terminated(self: Type[StreamingClient], event: TerminationEvent):
    print(f"Session terminated: {event.audio_duration_seconds} seconds of audio processed")

def on_error(self: Type[StreamingClient], error: StreamingError):
    print(f"Error occurred: {error}")

def main():
    client = StreamingClient(
        StreamingClientOptions(
            api_key=api_key,
            api_host="streaming.assemblyai.com",
        )
    )

    client.on(StreamingEvents.Begin, on_begin)
    client.on(StreamingEvents.Turn, on_turn)
    client.on(StreamingEvents.Termination, on_terminated)
    client.on(StreamingEvents.Error, on_error)

    client.connect(
        StreamingParameters(
            sample_rate=16000,
            format_turns=True,
            # Webhook parameters
            webhook_url="https://example.com/webhook",
            webhook_auth_header_name="X-Webhook-Secret",  # Optional
            webhook_auth_header_value="secret-value",  # Optional
        )
    )

    try:
        client.stream(aai.extras.MicrophoneStream(sample_rate=16000))
    finally:
        client.disconnect(terminate=True)

if __name__ == "__main__":
    main()

const WebSocket = require("ws");

const API_KEY = "<YOUR_API_KEY>";

const connectionParams = new URLSearchParams({
  sample_rate: 16000,
  format_turns: true,
  // Webhook parameters
  webhook_url: "https://example.com/webhook",
  webhook_auth_header_name: "X-Webhook-Secret", // Optional
  webhook_auth_header_value: "secret-value", // Optional
});

const API_ENDPOINT = `wss://streaming.assemblyai.com/v3/ws?${connectionParams.toString()}`;

const ws = new WebSocket(API_ENDPOINT, {
  headers: {
    Authorization: API_KEY,
  },
});

ws.on("open", () => {
  console.log("WebSocket connection opened.");
  console.log(`Connected to: ${API_ENDPOINT}`);

  // Start streaming audio data here
  // For example, using a microphone input library
});

ws.on("message", (data) => {
  try {
    const message = JSON.parse(data);
    const msgType = message.type;

    if (msgType === "Begin") {
      const sessionId = message.id;
      const expiresAt = new Date(message.expires_at * 1000);
      console.log(`\nSession began: ID=${sessionId}, ExpiresAt=${expiresAt}`);
    } else if (msgType === "Turn") {
      const transcript = message.transcript || "";
      if (message.end_of_turn) {
        process.stdout.write("\r" + " ".repeat(80) + "\r");
        console.log(transcript);
      } else {
        process.stdout.write(`\r${transcript}`);
      }
    } else if (msgType === "Termination") {
      const audioDuration = message.audio_duration_seconds || 0;
      const sessionDuration = message.session_duration_seconds || 0;
      console.log(
        `\nSession Terminated: Audio Duration=${audioDuration}s, Session Duration=${sessionDuration}s`
      );
    }
  } catch (e) {
    console.error("Error handling message:", e);
  }
});

ws.on("error", (error) => {
  console.error("WebSocket Error:", error);
});

ws.on("close", (code, reason) => {
  console.log(`WebSocket Disconnected: Status=${code}, Msg=${reason}`);
});

// To gracefully close the session, send a Terminate message
function terminateSession() {
  if (ws.readyState === WebSocket.OPEN) {
    ws.send(JSON.stringify({ type: "Terminate" }));
  }
}

import { Readable } from "stream";
import { AssemblyAI } from "assemblyai";
import recorder from "node-record-lpcm16";

const run = async () => {
  const client = new AssemblyAI({
    apiKey: "<YOUR_API_KEY>",
  });

  const transcriber = client.streaming.transcriber({
    sampleRate: 16_000,
    formatTurns: true,
    // Webhook parameters
    webhookUrl: "https://example.com/webhook",
    webhookAuthHeaderName: "X-Webhook-Secret", // Optional
    webhookAuthHeaderValue: "secret-value", // Optional
  });

  transcriber.on("open", ({ id }) => {
    console.log(`Session opened with ID: ${id}`);
  });

  transcriber.on("error", (error) => {
    console.error("Error:", error);
  });

  transcriber.on("close", (code, reason) =>
    console.log("Session closed:", code, reason)
  );

  transcriber.on("turn", (turn) => {
    if (!turn.transcript) {
      return;
    }
    console.log("Turn:", turn.transcript);
  });

  try {
    console.log("Connecting to streaming transcript service");
    await transcriber.connect();

    console.log("Starting recording");
    const recording = recorder.record({
      channels: 1,
      sampleRate: 16_000,
      audioType: "wav",
    });

    Readable.toWeb(recording.stream()).pipeTo(transcriber.stream());

    process.on("SIGINT", async function () {
      console.log();
      console.log("Stopping recording");
      recording.stop();

      console.log("Closing streaming transcript connection");
      await transcriber.close();

      process.exit();
    });
  } catch (error) {
    console.error(error);
  }
};

run();