Speech Recognition Development Tutorials, Guides & Insights

With AI assistants like Siri, Alexa, and Google Assistant becoming common, building your own lets you understand the underlying technologies while tailoring it to your specific needs.

Install the necessary libraries for speech recognition, text-to-speech, and automation:

Save the following code as audio_to_text.py.

import speech_recognition as sr
from pydub import AudioSegment

def convert_audio_to_text(audio_file_path):
    # Initialize recognizer
    recognizer = sr.Recognizer()

    # Convert audio file to wav format if necessary
    if not audio_file_path.endswith('.wav'):
        audio = AudioSegment.from_file(audio_file_path)
        audio_file_path = 'converted.wav'
        audio.export(audio_file_path, format='wav')

    # Load the audio file
    with sr.AudioFile(audio_file_path) as source:
        audio_data = recognizer.record(source)

    # Recognize and convert audio to text
    try:
        text = recognizer.recognize_google(audio_data)
        print("Transcribed Text:")
        print(text)
        return text
    except sr.UnknownValueError:
        print("Google Speech Recognition could not understand audio")
    except sr.RequestError as e:
        print(f"Could not request results from Google Speech Recognition service; {e}")

if __name__ == '__main__':
    audio_file = 'your_audio_file.wav'  # Replace with your audio file path
    convert_audio_to_text(audio_file)