Model selection

import logging
from typing import Type

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

api_key = "<YOUR_API_KEY>"

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

def on_begin(self: Type[StreamingClient], event: BeginEvent):
    print(f"Session started: {event.id}")

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,
            speech_model="u3-rt-pro",  # or "universal-streaming-english", "universal-streaming-multilingual", "whisper-rt"
            min_turn_silence=100,
            max_turn_silence=1000,
            # format_turns=True,  # Whether to return formatted final transcripts (not applicable to u3-rt-pro)
        )
    )

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

if __name__ == "__main__":
    main()

const WebSocket = require("ws");
const mic = require("mic");
const querystring = require("querystring");

const YOUR_API_KEY = "<YOUR_API_KEY>";
const CONNECTION_PARAMS = {
  sample_rate: 16000,
  speech_model: "u3-rt-pro", // or "universal-streaming-english", "universal-streaming-multilingual", "whisper-rt"
  min_turn_silence: 100,
  max_turn_silence: 1000,
  // format_turns: true, // Whether to return formatted final transcripts (not applicable to u3-rt-pro)
};
const API_ENDPOINT_BASE_URL = "wss://streaming.assemblyai.com/v3/ws";
const API_ENDPOINT = `${API_ENDPOINT_BASE_URL}?${querystring.stringify(CONNECTION_PARAMS)}`;

const SAMPLE_RATE = CONNECTION_PARAMS.sample_rate;

let micInstance = null;
let ws = null;

function run() {
  console.log("Starting AssemblyAI streaming transcription...");

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

  ws.on("open", () => {
    console.log("WebSocket connection opened.");

    micInstance = mic({
      rate: String(SAMPLE_RATE),
      channels: "1",
      bitwidth: "16",
      encoding: "signed-integer",
      endian: "little",
    });

    const micInputStream = micInstance.getAudioStream();
    micInputStream.on("data", (data) => {
      if (ws.readyState === WebSocket.OPEN) {
        ws.send(data);
      }
    });

    micInstance.start();
    console.log("Speak into your microphone. Press Ctrl+C to stop.");
  });

  ws.on("message", (data) => {
    try {
      const msg = JSON.parse(data);
      if (msg.type === "Begin") {
        console.log(`Session began: ID=${msg.id}`);
      } else if (msg.type === "Turn") {
        const transcript = msg.transcript || "";
        if (msg.end_of_turn) {
          process.stdout.write("\r" + " ".repeat(80) + "\r");
          console.log(transcript);
        } else {
          process.stdout.write(`\r${transcript}`);
        }
      } else if (msg.type === "Termination") {
        console.log(
          `\nSession terminated: ${msg.audio_duration_seconds}s of audio`
        );
      }
    } catch (e) {
      console.error("Error parsing message:", e);
    }
  });

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

  ws.on("close", (code, reason) => {
    console.log(`WebSocket closed: ${code}`);
    if (micInstance) micInstance.stop();
  });

  process.on("SIGINT", () => {
    console.log("\nStopping...");
    if (micInstance) micInstance.stop();
    if (ws && ws.readyState === WebSocket.OPEN) {
      ws.send(JSON.stringify({ type: "Terminate" }));
      setTimeout(() => ws.close(), 2000);
    }
  });
}

run();

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,
    speechModel: "u3-rt-pro", // or "universal-streaming-english", "universal-streaming-multilingual", "whisper-rt"
    minTurnSilence: 100,
    maxTurnSilence: 1000,
    // formatTurns: true, // Whether to return formatted final transcripts (not applicable to u3-rt-pro)
  });

  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();