Using real-time streaming

AssemblyAI's Real-Time Transcription service allows you to transcribe live audio streams with high accuracy and low latency. By streaming your audio data to our secure WebSocket API, you can receive transcripts back within a few hundred milliseconds, and our system continues to revise these transcripts with greater accuracy over time as more context arrives.

In this guide, you'll learn how to establish a WebSocket connection, send audio data, and receive partial and final transcription results. Real-Time Transcription requires 16-bit signed integer PCM-encoded, single-channel audio, matching a predefined sample rate. You can send between 100 and 2000 milliseconds of audio over a WebSocket at a time.

Get started

Before we begin, make sure you have an AssemblyAI account and an API key. You can sign up for a free account and get your API key from your dashboard. Please note that this feature is available for paid accounts only. If you're on the free plan, you'll need to upgrade.

The entire source code of this guide can be viewed here.

Step-by-step instructions

1. 1

   To use the microphone stream you need to install pyaudio. Mac and Linux users also need to install portaudio first. Additionally, install the websocket-client package:

   # (Mac)
   brew install portaudio
   
   # (Debian/Ubuntu)
   apt install portaudio19-dev
   
   pip install pyaudio
   pip install websocket-client

   In your code, first setup the microphone stream and then establish a WebSocket connection with the real-time endpoint by using a WebSocket client and connecting to wss://api.assemblyai.com/v2/realtime/ws.

   Authenticate your request by including your API key in the authorization header of your WebSocket connection, and provide the sample rate of your audio data as a query parameter to the real-time endpoint.

2. 2

   Update the WebSocket's message event to load the incoming data as JSON and extract the text

3. 3

   Update the WebSocket's message event to print the transcript, conditionally prepended with a string that signifies if the transcript is partial or final.

4. 4

   Update the WebSocket's open event to stream data from the microphone, sent base-64 encoded via JSON

5. 5

   Optional: Add up to 2,500 characters of custom vocabulary to your real-time session by including the word_boost parameter as an optional query parameter in the URL.

   See also Adding Custom Vocabulary

6. 6

   Update the WebSocket's error event to handle WebSocket errors and application-level errors, including bad sample rate, authentication failure, insufficient funds, and more. See also Closing and Status Codes for a list of errors.

   Additionally, update the WebSocket's close event.

Audio Requirements

The raw audio data in the audio_data field above must comply with a strict encoding format. This is because we don't do any transcoding to your data, we send it directly to the model for transcription to reduce latency. The encoding of your audio must be in:

• WAV PCM16
• A sample rate that matches the value of the sample_rate query param you supply
• Single-channel
• 100 to 2000 milliseconds of audio per message

Request Types

These are the types of requests that can be sent to the WebSocket API.

Opening a Session

When opening a Session you can pass the following query attributes to the WebSocket URL:

sample_rate

The sample rate of the streamed audio.

Example: wss://api.assemblyai.com/v2/realtime/ws?sample_rate=16000

word_boost

See also Adding Custom Vocabulary

token

See also Creating Temporary Authentication Tokens

Sending Audio

When sending audio over the WebSocket connection, you should send a JSON payload with the following parameters:

Field	Example	Description
audio_data	"UklGRtjIAABXQVZFZ"	Raw audio data, base64 encoded. This can be the raw data recorded directly from a microphone or read from an audio file.

Terminating a Session

When you've completed your session, clients should send a JSON message with the following field.

Field	Example	Description
terminate_session	true	A boolean value to communicate that you wish to end your real-time session forever.

After requesting session termination, the server will send the remaining transcript messages, followed by a SessionTerminated message.

Response Types

These are the types of responses that can be received from the WebSocket API.

Session Start

Once your request is authorized and connection established, your client receives a SessionBegins message with the following JSON data:

Field	Example	Description
message_type	"SessionBegins"	Describes the type of the message.
session_id	"d3e8c537-2f11-494b-b497-e59a434588bd"	Unique identifier for the established session.
expires_at	"2023-05-24T08:09:10.161850"	Timestamp when this session will expire.

Transcripts

Our Real-Time Transcription pipeline uses a two-phase transcription strategy, broken into partial and final results.

Partial Transcripts

As you send audio data to the API, the API immediately starts responding with Partial Results. The following keys are returned from the WebSocket API.

Field	Example	Description
message_type	"PartialTranscript"	Describes the type of message.
audio_start	0	Start time of audio sample relative to session start, in milliseconds.
audio_end	1500	End time of audio sample relative to session start, in milliseconds.
confidence	0.987190506414702	The confidence score of the entire transcription, between 0 and 1.
text	"there is a house in new orleans"	The partial transcript for your audio.
words	[{"start": 0, "end": 440, "confidence": 1.0, "text": "there"}, ...]	An array of objects, with the information for each word in the transcription text. Includes the start/end time (in milliseconds) of the word, the confidence score of the word, and the text (i.e. the word itself).
created	"2023-05-24T08:09:10.161850"	The timestamp for the partial transcript.

Final Transcripts

After you've received your partial results, our model continues to analyze incoming audio and, when it detects the end of an "utterance" (usually a pause in speech), it'll finalize the results sent to you so far with higher accuracy, as well as add punctuation and casing to the transcription text.

The following keys are returned from the WebSocket API when Final Results are sent:

Field	Example	Description
message_type	"FinalTranscript"	Describes the type of message.
audio_start	0	Start time of audio sample relative to session start, in milliseconds.
audio_end	1500	End time of audio sample relative to session start, in milliseconds.
confidence	0.997190506414702	The confidence score of the entire transcription, between 0 and 1.
text	"There is a house in New Orleans"	The partial transcript for your audio.
words	[{"start": 0, "end": 440, "confidence": 1.0, "text": "There"}, ...]	An array of objects, with the information for each word in the transcription text. Includes the start/end time (in milliseconds) of the word, the confidence score of the word, and the text (i.e. the word itself).
created	"2023-05-24T08:09:10.161850"	The timestamp for the final transcript.
punctuated	true	Whether the text has been punctuated and cased.
text_formatted	true	Whether the text has been formatted (e.g. Dollar -> $)

Session Terminated

After requesting session termination, the server will send the remaining transcript messages, followed by a SessionTerminated message. Your client receives a SessionTerminated message with the following JSON data:

Field	Example	Description
message_type	"SessionTerminated"	Describes the type of the message.

Closing and Status Codes

The WebSocket specification provides standard errors.

Our API provides application-level WebSocket errors for well-known scenarios:

Error Condition	Status Code	Message
bad sample rate	4000	"Sample rate must be a positive integer"
auth failed	4001	"Not Authorized"
insufficient funds	4002	"Insufficient Funds"
free tier user	4002	"This feature is paid-only and requires you to add a credit card. Please visit https://app.assemblyai.com/ to add a credit card to your account"
attempt to connect to nonexistent session id	4004	"Session not found"
session expired	4008	"Session Expired"
attempt to connect to closed session	4010	"Session previously closed"
rate limited	4029	"Client sent audio too fast"
unique session violation	4030	"Session is handled by another WebSocket"
session times out	4031	"Session idle for too long"
audio too short	4032	"Audio duration is too short"
audio too long	4033	"Audio duration is too long"
bad json	4100	"Endpoint received invalid JSON"
bad schema	4101	"Endpoint received a message with an invalid schema"
too many streams	4102	"This account has exceeded the number of allowed streams"
reconnected	4103	"This session has been reconnected. This WebSocket is no longer valid."
reconnect attempts exhausted	1013	"Temporary server condition forced blocking client's request"

Quotas and Limits

The following limits are imposed to ensure performance and service quality.

• Idle Sessions - Sessions that don't receive audio within 1 minute will be terminated.
• Session Limit - 32 sessions at a time for paid users. Please contact us if you need to increase this limit. Free-tier users must upgrade their account to use real-time streaming.
• Session Uniqueness - Only one WebSocket per session.
• Audio Sampling Rate Limit - Customers must send data in near real-time. If a client sends data faster than 1 second of audio per second for longer than 1 minute, we'll terminate the session.

Adding Custom Vocabulary

Developers can also add up to 2500 characters of custom vocabulary to their real-time session by adding the optional query parameter word_boost in the URL. The parameter should map to a JSON encoded list of strings as shown in this Python example:

import json
from urllib.parse import urlencode

sample_rate = 16000
word_boost = ["foo", "bar"]
params = {"sample_rate": sample_rate, "word_boost": json.dumps(word_boost)}

url = f"wss://api.assemblyai.com/v2/realtime/ws?{urlencode(params)}"

Creating Temporary Authentication Tokens

In some cases, a developer needs to authenticate on the client-side and doesn't want to expose their AssemblyAI API key. You can do this by sending a POST request to https://api.assemblyai.com/v2/realtime/token with the parameter expires_in: {TTL in seconds}. Below is a quick example in curl.

note

The expires_in parameter must be greater than or equal to 60 seconds.

curl --request POST \
  --url https://api.assemblyai.com/v2/realtime/token \
  --header 'authorization: YOUR_API_TOKEN' \
  --header 'Content-Type: application/json' \
  --data '{"expires_in": 60}'

In response you'll receive the following JSON output:

{
  "token": "b2e3c6c71d450589b2f4f0bb1ac4efd2d5e55b1f926e552e02fc0cc070eaedbd"
}

A developer can now use this temporary token in the browser to authenticate a new WebSocket session with the following endpoint wss://api.assemblyai.com/v2/realtime/ws?sample_rate=16000&token={New Temp Token}. For example:

let socket
const token = 'b2e3c6c71d450589b2f4f0bb1ac4efd2d5e55b1f926e552e02fc0cc070eaedbd'

socket = new WebSocket(
  `wss://api.assemblyai.com/v2/realtime/ws?sample_rate=16000&token=${token}`
)

Conclusion

Real-Time Transcription is a powerful feature with even more powerful possibilities for integration. On the AssemblyAI blog, you can learn about using Real-Time Transcription to:

• Automatically Transcribe Zoom Calls in Real Time
• Transcribe Twilio Phone Calls
• Connect to the Real-Time Transcription API using a PyAudio stream

You can also find an example of using Express.js for Real-Time Transcription on GitHub.