Use this file to discover all available pages before exploring further.
speech_model is requiredYou must include the speech_model parameter in every streaming transcription request. There is no default model. If you omit speech_model, the request will fail. See Model selection to learn about available models.
Streaming is now available in EU-West via streaming.eu.assemblyai.com. To
use the EU streaming endpoint, replace streaming.assemblyai.com with
streaming.eu.assemblyai.com in your connection configuration.
Streaming is billed per sessionUniversal Streaming is billed on the total duration that your WebSocket connection stays open, not on the amount of audio you send. Always send a Terminate message when you’re done with a stream — sessions that aren’t closed auto-close after 3 hours and are billed for the full duration. See Billing and pricing for details.
In this quick guide you will learn how to use AssemblyAI’s Streaming Speech-to-Text feature to transcribe audio from your microphone.To run this quickstart you will need:
import pyaudioimport websocketimport jsonimport threadingimport timeimport wavefrom urllib.parse import urlencodefrom datetime import datetime# --- Configuration ---YOUR_API_KEY = "YOUR-API-KEY" # Replace with your actual API keyCONNECTION_PARAMS = { "sample_rate": 16000, "speech_model": "universal-streaming-english", "format_turns": True, # Request formatted final transcripts}API_ENDPOINT_BASE_URL = "wss://streaming.assemblyai.com/v3/ws"API_ENDPOINT = f"{API_ENDPOINT_BASE_URL}?{urlencode(CONNECTION_PARAMS)}"# Audio ConfigurationFRAMES_PER_BUFFER = 800 # 50ms of audio (0.05s * 16000Hz)SAMPLE_RATE = CONNECTION_PARAMS["sample_rate"]CHANNELS = 1FORMAT = pyaudio.paInt16# Global variables for audio stream and websocketaudio = Nonestream = Nonews_app = Noneaudio_thread = Nonestop_event = threading.Event() # To signal the audio thread to stop# WAV recording variablesrecorded_frames = [] # Store audio frames for WAV filerecording_lock = threading.Lock() # Thread-safe access to recorded_frames# --- WebSocket Event Handlers ---def on_open(ws): """Called when the WebSocket connection is established.""" print("WebSocket connection opened.") print(f"Connected to: {API_ENDPOINT}") # Start sending audio data in a separate thread def stream_audio(): global stream print("Starting audio streaming...") while not stop_event.is_set(): try: audio_data = stream.read(FRAMES_PER_BUFFER, exception_on_overflow=False) # Store audio data for WAV recording with recording_lock: recorded_frames.append(audio_data) # Send audio data as binary message ws.send(audio_data, websocket.ABNF.OPCODE_BINARY) except Exception as e: print(f"Error streaming audio: {e}") # If stream read fails, likely means it's closed, stop the loop break print("Audio streaming stopped.") global audio_thread audio_thread = threading.Thread(target=stream_audio) audio_thread.daemon = ( True # Allow main thread to exit even if this thread is running ) audio_thread.start()def on_message(ws, message): try: data = json.loads(message) msg_type = data.get('type') if msg_type == "Begin": session_id = data.get('id') expires_at = data.get('expires_at') print(f"\nSession began: ID={session_id}, ExpiresAt={datetime.fromtimestamp(expires_at)}") elif msg_type == "Turn": transcript = data.get('transcript', '') if data.get('end_of_turn'): print('\r' + ' ' * 80 + '\r', end='') print(transcript) else: print(f"\r{transcript}", end='') elif msg_type == "Termination": audio_duration = data.get('audio_duration_seconds', 0) session_duration = data.get('session_duration_seconds', 0) print(f"\nSession Terminated: Audio Duration={audio_duration}s, Session Duration={session_duration}s") except json.JSONDecodeError as e: print(f"Error decoding message: {e}") except Exception as e: print(f"Error handling message: {e}")def on_error(ws, error): """Called when a WebSocket error occurs.""" print(f"\nWebSocket Error: {error}") # Attempt to signal stop on error stop_event.set()def on_close(ws, close_status_code, close_msg): """Called when the WebSocket connection is closed.""" print(f"\nWebSocket Disconnected: Status={close_status_code}, Msg={close_msg}") # Save recorded audio to WAV file save_wav_file() # Ensure audio resources are released global stream, audio stop_event.set() # Signal audio thread just in case it's still running if stream: if stream.is_active(): stream.stop_stream() stream.close() stream = None if audio: audio.terminate() audio = None # Try to join the audio thread to ensure clean exit if audio_thread and audio_thread.is_alive(): audio_thread.join(timeout=1.0)def save_wav_file(): """Save recorded audio frames to a WAV file.""" if not recorded_frames: print("No audio data recorded.") return # Generate filename with timestamp timestamp = datetime.now().strftime("%Y%m%d_%H%M%S") filename = f"recorded_audio_{timestamp}.wav" try: with wave.open(filename, 'wb') as wf: wf.setnchannels(CHANNELS) wf.setsampwidth(2) # 16-bit = 2 bytes wf.setframerate(SAMPLE_RATE) # Write all recorded frames with recording_lock: wf.writeframes(b''.join(recorded_frames)) print(f"Audio saved to: {filename}") print(f"Duration: {len(recorded_frames) * FRAMES_PER_BUFFER / SAMPLE_RATE:.2f} seconds") except Exception as e: print(f"Error saving WAV file: {e}")# --- Main Execution ---def run(): global audio, stream, ws_app # Initialize PyAudio audio = pyaudio.PyAudio() # Open microphone stream try: stream = audio.open( input=True, frames_per_buffer=FRAMES_PER_BUFFER, channels=CHANNELS, format=FORMAT, rate=SAMPLE_RATE, ) print("Microphone stream opened successfully.") print("Speak into your microphone. Press Ctrl+C to stop.") print("Audio will be saved to a WAV file when the session ends.") except Exception as e: print(f"Error opening microphone stream: {e}") if audio: audio.terminate() return # Exit if microphone cannot be opened # Create WebSocketApp ws_app = websocket.WebSocketApp( API_ENDPOINT, header={"Authorization": YOUR_API_KEY}, on_open=on_open, on_message=on_message, on_error=on_error, on_close=on_close, ) # Run WebSocketApp in a separate thread to allow main thread to catch KeyboardInterrupt ws_thread = threading.Thread(target=ws_app.run_forever) ws_thread.daemon = True ws_thread.start() try: # Keep main thread alive until interrupted while ws_thread.is_alive(): time.sleep(0.1) except KeyboardInterrupt: print("\nCtrl+C received. Stopping...") stop_event.set() # Signal audio thread to stop # Send termination message to the server if ws_app and ws_app.sock and ws_app.sock.connected: try: terminate_message = {"type": "Terminate"} print(f"Sending termination message: {json.dumps(terminate_message)}") ws_app.send(json.dumps(terminate_message)) # Give a moment for messages to process before forceful close time.sleep(5) except Exception as e: print(f"Error sending termination message: {e}") # Close the WebSocket connection (will trigger on_close) if ws_app: ws_app.close() # Wait for WebSocket thread to finish ws_thread.join(timeout=2.0) except Exception as e: print(f"\nAn unexpected error occurred: {e}") stop_event.set() if ws_app: ws_app.close() ws_thread.join(timeout=2.0) finally: # Final cleanup (already handled in on_close, but good as a fallback) if stream and stream.is_active(): stream.stop_stream() if stream: stream.close() if audio: audio.terminate() print("Cleanup complete. Exiting.")if __name__ == "__main__": run()
const WebSocket = require("ws");const mic = require("mic");const querystring = require("querystring");const fs = require("fs");// --- Configuration ---const YOUR_API_KEY = "YOUR-API-KEY"; // Replace with your actual API keyconst CONNECTION_PARAMS = { sample_rate: 16000, speech_model: "universal-streaming-english", format_turns: true, // Request formatted final transcripts};const API_ENDPOINT_BASE_URL = "wss://streaming.assemblyai.com/v3/ws";const API_ENDPOINT = `${API_ENDPOINT_BASE_URL}?${querystring.stringify(CONNECTION_PARAMS)}`;// Audio Configurationconst SAMPLE_RATE = CONNECTION_PARAMS.sample_rate;const CHANNELS = 1;// Global variableslet micInstance = null;let micInputStream = null;let ws = null;let stopRequested = false;// WAV recording variableslet recordedFrames = []; // Store audio frames for WAV file// --- Helper functions ---function clearLine() { process.stdout.write("\r" + " ".repeat(80) + "\r");}function formatTimestamp(timestamp) { return new Date(timestamp * 1000).toISOString();}function createWavHeader(sampleRate, channels, dataLength) { const buffer = Buffer.alloc(44); // RIFF header buffer.write("RIFF", 0); buffer.writeUInt32LE(36 + dataLength, 4); buffer.write("WAVE", 8); // fmt chunk buffer.write("fmt ", 12); buffer.writeUInt32LE(16, 16); // fmt chunk size buffer.writeUInt16LE(1, 20); // PCM format buffer.writeUInt16LE(channels, 22); buffer.writeUInt32LE(sampleRate, 24); buffer.writeUInt32LE(sampleRate * channels * 2, 28); // byte rate buffer.writeUInt16LE(channels * 2, 32); // block align buffer.writeUInt16LE(16, 34); // bits per sample // data chunk buffer.write("data", 36); buffer.writeUInt32LE(dataLength, 40); return buffer;}function saveWavFile() { if (recordedFrames.length === 0) { console.log("No audio data recorded."); return; } // Generate filename with timestamp const timestamp = new Date().toISOString().replace(/[:.]/g, "-").slice(0, 19); const filename = `recorded_audio_${timestamp}.wav`; try { // Combine all recorded frames const audioData = Buffer.concat(recordedFrames); const dataLength = audioData.length; // Create WAV header const wavHeader = createWavHeader(SAMPLE_RATE, CHANNELS, dataLength); // Write WAV file const wavFile = Buffer.concat([wavHeader, audioData]); fs.writeFileSync(filename, wavFile); console.log(`Audio saved to: ${filename}`); console.log( `Duration: ${(dataLength / (SAMPLE_RATE * CHANNELS * 2)).toFixed(2)} seconds` ); } catch (error) { console.error(`Error saving WAV file: ${error}`); }}// --- Main function ---async function run() { console.log("Starting AssemblyAI real-time transcription..."); console.log("Audio will be saved to a WAV file when the session ends."); // Initialize WebSocket connection ws = new WebSocket(API_ENDPOINT, { headers: { Authorization: YOUR_API_KEY, }, }); // Setup WebSocket event handlers ws.on("open", () => { console.log("WebSocket connection opened."); console.log(`Connected to: ${API_ENDPOINT}`); // Start the microphone startMicrophone(); }); ws.on("message", (message) => { try { const data = JSON.parse(message); const msgType = data.type; if (msgType === "Begin") { const sessionId = data.id; const expiresAt = data.expires_at; console.log( `\nSession began: ID=${sessionId}, ExpiresAt=${formatTimestamp(expiresAt)}` ); } else if (msgType === "Turn") { const transcript = data.transcript || ""; if (data.end_of_turn) { clearLine(); console.log(transcript); } else { process.stdout.write(`\r${transcript}`); } } else if (msgType === "Termination") { const audioDuration = data.audio_duration_seconds; const sessionDuration = data.session_duration_seconds; console.log( `\nSession Terminated: Audio Duration=${audioDuration}s, Session Duration=${sessionDuration}s` ); } } catch (error) { console.error(`\nError handling message: ${error}`); console.error(`Message data: ${message}`); } }); ws.on("error", (error) => { console.error(`\nWebSocket Error: ${error}`); cleanup(); }); ws.on("close", (code, reason) => { console.log(`\nWebSocket Disconnected: Status=${code}, Msg=${reason}`); cleanup(); }); // Handle process termination setupTerminationHandlers();}function startMicrophone() { try { micInstance = mic({ rate: SAMPLE_RATE.toString(), channels: CHANNELS.toString(), debug: false, exitOnSilence: 6, // This won't actually exit, just a parameter for mic }); micInputStream = micInstance.getAudioStream(); micInputStream.on("data", (data) => { if (ws && ws.readyState === WebSocket.OPEN && !stopRequested) { // Store audio data for WAV recording recordedFrames.push(Buffer.from(data)); // Send audio data to WebSocket ws.send(data); } }); micInputStream.on("error", (err) => { console.error(`Microphone Error: ${err}`); cleanup(); }); micInstance.start(); console.log("Microphone stream opened successfully."); console.log("Speak into your microphone. Press Ctrl+C to stop."); } catch (error) { console.error(`Error opening microphone stream: ${error}`); cleanup(); }}function cleanup() { stopRequested = true; // Save recorded audio to WAV file saveWavFile(); // Stop microphone if it's running if (micInstance) { try { micInstance.stop(); } catch (error) { console.error(`Error stopping microphone: ${error}`); } micInstance = null; } // Close WebSocket connection if it's open if (ws && [WebSocket.OPEN, WebSocket.CONNECTING].includes(ws.readyState)) { try { // Send termination message if possible if (ws.readyState === WebSocket.OPEN) { const terminateMessage = { type: "Terminate" }; console.log( `Sending termination message: ${JSON.stringify(terminateMessage)}` ); ws.send(JSON.stringify(terminateMessage)); } ws.close(); } catch (error) { console.error(`Error closing WebSocket: ${error}`); } ws = null; } console.log("Cleanup complete.");}function setupTerminationHandlers() { // Handle Ctrl+C and other termination signals process.on("SIGINT", () => { console.log("\nCtrl+C received. Stopping..."); cleanup(); // Give time for cleanup before exiting setTimeout(() => process.exit(0), 1000); }); process.on("SIGTERM", () => { console.log("\nTermination signal received. Stopping..."); cleanup(); // Give time for cleanup before exiting setTimeout(() => process.exit(0), 1000); }); // Handle uncaught exceptions process.on("uncaughtException", (error) => { console.error(`\nUncaught exception: ${error}`); cleanup(); // Give time for cleanup before exiting setTimeout(() => process.exit(1), 1000); });}// Start the applicationrun();
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: "universal-streaming-english", formatTurns: true, }); 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", // Linear PCM }); Readable.toWeb(recording.stream()).pipeTo(transcriber.stream()); // Stop recording and close connection using Ctrl-C. 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();
Log the session ID for every connectionThe Begin event includes an id field — this is the session ID. We strongly recommend persisting it (along with a timestamp and the API region) for every streaming session, not just when you hit an error. If you ever need to contact support@assemblyai.com about a session, including this ID lets us locate it in our logs immediately. The same applies to the close_code and close_reason returned when the WebSocket terminates — log these alongside the session ID. See Common session errors and closures for the full list of close codes.
A Turn object is intended to correspond to a speaking turn in the context of voice agent applications, and therefore it roughly corresponds to an utterance in a broader context. We assign a unique ID to each Turn object, which is included in our response. Specifically, the Universal-Streaming response is formatted as follows:
turn_order: Integer that increments with each new turn
turn_is_formatted: Boolean indicating if the text in the transcript field has been formatted with punctuation, casing, and inverse text normalization (e.g. dates, times, phone numbers). This field is false by default. Set format_turns=true to enable formatting. Use end_of_turn to detect end of turn, not turn_is_formatted.
end_of_turn: Boolean indicating if this is the end of the current turn
transcript: String containing only finalized words
end_of_turn_confidence: Floating number (0-1) representing the confidence that the current turn has finished, i.e., the current speaker has completed their turn
words: List of Word objects with individual metadata
Each Word object in the words array includes:
text: The string representation of the word
word_is_final: Boolean indicating if the word is finalized, where a finalized word means the word won’t be altered in future transcription responses
start: Timestamp for word start
end: Timestamp for word end
confidence: Confidence score for the word
Do not use turn_is_formatted to detect end of turn. Use end_of_turn
to determine when a speaker’s turn has completed.
AssemblyAI’s streaming system receives audio in a streaming fashion, it returns transcription responses in real-time using the format specified above. Unlike many other streaming speech-to-text models that implement the concept of partial/variable transcriptions to show transcripts in an ongoing manner, Universal-Streaming transcriptions are immutable. In other words, the text that has already been produced will not be overwritten in future transcription responses. Therefore, with Universal-Streaming, the transcriptions will be delivered in the following way:
→ Hello my na→ Hello my name→ Hello my name→ Hello my name is→ Hello my name is Zac→ Hello my name is Zack
When an end of the current turn is detected, you receive a message with end_of_turn set to true. If you enable text formatting by setting format_turns=true, you will also receive a transcription response with turn_is_formatted set to true.
→ Hello my name is Zack→ Hello, my name is Zack. (end_of_turn: true)
In this example, you may have noticed that the last word of each transcript may occasionally be a subword (“Zac” in the example shown above). Each Word object has the word_is_final field to indicate whether the model is confident that the last word is a completed word. Note that, except for the last word, word_is_final is always true.
The following parameters can be updated mid-stream:
end_of_turn_confidence_threshold — Adjust the confidence threshold for end-of-turn detection. Higher values require more confidence before ending a turn. See Turn Detection for details.
min_turn_silence — Minimum silence duration in milliseconds before an end-of-turn check fires. Lower values produce faster turn endings, while higher values reduce entity splitting.
max_turn_silence — Maximum silence in milliseconds before forcing a turn to end, regardless of confidence. Increase for moments where you’d expect a longer pause, such as when a caller is reading out a credit card number or address.
vad_threshold — The confidence threshold (0.0 to 1.0) for classifying audio frames as speech. Increase for noisy environments to reduce false speech detection.
keyterms_prompt — A list of words and phrases to boost recognition accuracy for. Dynamically update based on the current stage of your conversation. See Keyterms Prompting for details.