Transcribe streaming audio from a microphone in Python

Overview

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

Before you begin

To complete this tutorial, you need:

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

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

1
import assemblyai as aai
2
3
aai.settings.api_key = "<YOUR_API_KEY>"
4
5
6
def on_open(session_opened: aai.RealtimeSessionOpened):
7
    print("Session ID:", session_opened.session_id)
8
9
10
def on_data(transcript: aai.RealtimeTranscript):
11
    if not transcript.text:
12
        return
13
14
    if isinstance(transcript, aai.RealtimeFinalTranscript):
15
        print(transcript.text, end="\r\n")
16
    else:
17
        print(transcript.text, end="\r")
18
19
20
def on_error(error: aai.RealtimeError):
21
    print("An error occurred:", error)
22
23
24
def on_close():
25
    print("Closing Session")
26
27
28
transcriber = aai.RealtimeTranscriber(
29
    sample_rate=16_000,
30
    on_data=on_data,
31
    on_error=on_error,
32
    on_open=on_open,
33
    on_close=on_close,
34
)
35
36
transcriber.connect()
37
38
microphone_stream = aai.extras.MicrophoneStream(sample_rate=16_000)
39
transcriber.stream(microphone_stream)
40
41
transcriber.close()

Step 1: Install dependencies

$
brew install portaudio

$
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
import assemblyai as aai
2
3
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
def on_open(session_opened: aai.RealtimeSessionOpened):
2
    print("Session opened with ID:", session_opened.session_id)
3
4
5
def on_error(error: aai.RealtimeError):
6
    print("Error:", error)
7
8
9
def on_close():
10
    print("Session closed")

1
def on_data(transcript: aai.RealtimeTranscript):
2
    if not transcript.text:
3
        return
4
5
    if isinstance(transcript, aai.RealtimeFinalTranscript):
6
        # Add new line after final transcript.
7
        print(transcript.text, end="\r\n")
8
    else:
9
        print(transcript.text, end="\r")

1
transcriber = aai.RealtimeTranscriber(
2
    sample_rate=16_000,
3
    on_data=on_data,
4
    on_error=on_error,
5
    on_open=on_open,
6
    on_close=on_close,
7
)

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.

1
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
microphone_stream = aai.extras.MicrophoneStream(sample_rate=16_000)

1
transcriber.stream(microphone_stream)

Step 6: Close the connection

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

1
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:

• Streaming Speech-to-Text
• WebSocket API reference

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.