Get Started

1. Install Soniox Package

Install Soniox Python package. The package includes core functionality for accessing Soniox API.

pip3 install --upgrade pip
pip3 install --upgrade setuptools
pip3 install soniox

2. Create Soniox Account

Create a Soniox Account to obtain an API key. The API key gives you free access to Soniox speech recognition. You can find your API key under Developer tab in Soniox Cloud.

3. Try It Out

This example demonstrates how to use Soniox speech recognition for live transcription of audio from your microphone. You can copy/paste the code and run with python3. Do not forget to use your API key. You can terminate the live transcription by pressing Ctrl+C.

from soniox.transcribe_live import transcribe_microphone
from soniox.speech_service import Client, set_api_key


def main():
    with Client() as client:
        print("Transcribing from your microphone ...")
        for result in transcribe_microphone(client):
            print(" ".join(w.text for w in result.words))

if __name__ == "__main__":

Next Steps

Check out the Tutorial, where you will learn all about the Soniox speech recognition, data structures and usage patterns.

Check out the Applications for more advanced use cases of speech recognition.

Download the code examples. All code examples from the Tutorial and Applications in one place.


Let us know your feedback! If you encounter any problems, reach out to us. We will gladly help you out!