Skip to main content

Transcribe streaming audio from a microphone in Python

Learn how to transcribe streaming audio in Python.

Overview​

By the end of this tutorial, you'll be able to transcribe audio from your microphone in Python.

Supported languages

Streaming Speech-to-Text is only available for English.

Before you begin​

To complete this tutorial, you need:

  • Python installed.
  • An with a credit card set up.

Here's the full sample code of what you'll build in this tutorial:

import assemblyai as aai

aai.settings.api_key = "YOUR_API_KEY" 


def on_open(session_opened: aai.RealtimeSessionOpened):
    print("Session ID:", session_opened.session_id)


def on_data(transcript: aai.RealtimeTranscript):
    if not transcript.text:
        return

    if isinstance(transcript, aai.RealtimeFinalTranscript):
        print(transcript.text, end="\r\n")
    else:
        print(transcript.text, end="\r")


def on_error(error: aai.RealtimeError):
    print("An error occurred:", error)


def on_close():
    print("Closing Session")


transcriber = aai.RealtimeTranscriber(
    sample_rate=16_000,
    on_data=on_data,
    on_error=on_error,
    on_open=on_open,
    on_close=on_close,
)

transcriber.connect()

microphone_stream = aai.extras.MicrophoneStream(sample_rate=16_000)
transcriber.stream(microphone_stream)

transcriber.close()

Step 1: Install dependencies​

  1. 1

    PortAudio is a cross-platform library for streaming audio. The Python SDK uses PortAudio to stream audio from your microphone.

  2. 2

    Install the package via pip. extras enable additional features, such as streaming audio from a microphone.

    pip install "assemblyai[extras]"

Step 2: Configure the API key​

In this step, you 'll create an SDK client and configure it to use your API key.

  1. 1

    Browse to , and then click Copy API key under Copy your API key.

  2. 2

    Configure the SDK to use your API key. Replace YOUR_API_KEY with your copied API key.

    import assemblyai as aai

    aai.settings.api_key = "YOUR_API_KEY"

Step 3: Create a transcriber​

In this step, you'll set up a real-time transcriber object and callback functions that handle the different events.

  1. 1

    Create functions to handle events from the real-time transcriber.

    def on_open(session_opened: aai.RealtimeSessionOpened):
        print("Session opened with ID:", session_opened.session_id)


    def on_error(error: aai.RealtimeError):
        print("Error:", error)


    def on_close():
        print("Session closed")
  2. 2

    Create another function to handle transcripts. The real-time transcriber returns two types of transcripts: RealtimeFinalTranscript and RealtimePartialTranscript.

    • Partial transcripts are returned as the audio is being streamed to AssemblyAI.
    • Final transcripts are returned after a moment of silence.
    End of utterance controls

    You can configure the silence threshold for automatic utterance detection and programmatically force the end of an utterance to immediately get a Final transcript.

    def on_data(transcript: aai.RealtimeTranscript):
        if not transcript.text:
            return

        if isinstance(transcript, aai.RealtimeFinalTranscript):
            # Add new line after final transcript.
            print(transcript.text, end="\r\n")
        else:
            print(transcript.text, end="\r")
  3. 3

    Create a new RealtimeTranscriber using the function you created.

    transcriber = aai.RealtimeTranscriber(
        sample_rate=16_000,
        on_data=on_data,
        on_error=on_error,
        on_open=on_open,
        on_close=on_close,
    )
    Sample rate

    The sample_rate is the number of audio samples per second, measured in hertz (Hz). Higher sample rates result in higher quality audio, which may lead to better transcripts, but also more data being sent over the network.

    We recommend the following sample rates:

    • Minimum quality: 8_000 (8 kHz)
    • Medium quality: 16_000 (16 kHz)
    • Maximum quality: 48_000 (48 kHz)

Step 4: Connect the transcriber​

Streaming Speech-to-Text uses WebSockets to stream audio to AssemblyAI. This requires first establishing a connection to the API.

transcriber.connect()

The on_open function you created earlier will be called when the connection has been established.

Step 5: Record audio from microphone​

In this step, you'll configure your Python app to record audio from your microphone. You'll use a helper class from the Python SDK that make this easier.

  1. 1

    Open a microphone stream. The sample_rate needs to be the same value as the one you passed to RealtimeTranscriber.

    microphone_stream = aai.extras.MicrophoneStream(sample_rate=16_000)
    Audio data format

    MicrophoneStream formats the audio data for you. If you want to stream data from elsewhere, make sure that your audio data is in the following format:

    • Single channel
    • 16-bit signed integer PCM or mu-law encoding

    By default, transcriptions expect PCM16-encoded audio. If you want to use mu-law encoding, see Specifying the encoding.

  2. 2

    Start sending data from the microphone stream. The on_data function you created earlier will be called when the transcript is sent back.

    Press Ctrl+C to stop recording.

    transcriber.stream(microphone_stream)

Step 6: Close the connection​

Finally, close the connection when you're done to disconnect the transcriber.

transcriber.close()

The on_close function you created earlier will be called when the connection has been closed.

Next steps​

To learn more about Streaming Speech-to-Text, see the following resources:

Need some help?​

If you get stuck, or have any other questions, we'd love to help you out. Contact our support team at support@assemblyai.com or create a support ticket.

© AssemblyAI