python voice to text code example

Example 1: python text to speech

The best library because you dont have to save the
text file or open the file to start the speech

pip install pyttsx3

import pyttsx3
engine = pyttsx3.init()
engine.say("Hello world")
engine.runAndWait()

Example 2: python speech to text

import speech_recognition as sr


        def main():

            r = sr.Recognizer()

            with sr.Microphone() as source:
                r.adjust_for_ambient_noise(source)

                audio = r.listen(source)

                try:

                    print(r.recognize_google(audio))

                except Exception as e:
                    print("Error :  " + str(e))


                with open("recorded.wav", "wb") as f:
                    f.write(audio.get_wav_data())


        if __name__ == "__main__":
            main()

Example 3: python code voice to text

# importing libraries 
import speech_recognition as sr 
import os 
from pydub import AudioSegment
from pydub.silence import split_on_silence

# create a speech recognition object
r = sr.Recognizer()

# a function that splits the audio file into chunks
# and applies speech recognition
def get_large_audio_transcription(path):
    """
    Splitting the large audio file into chunks
    and apply speech recognition on each of these chunks
    """
    # open the audio file using pydub
    sound = AudioSegment.from_wav(path)  
    # split audio sound where silence is 700 miliseconds or more and get chunks
    chunks = split_on_silence(sound,
        # experiment with this value for your target audio file
        min_silence_len = 500,
        # adjust this per requirement
        silence_thresh = sound.dBFS-14,
        # keep the silence for 1 second, adjustable as well
        keep_silence=500,
    )
    folder_name = "audio-chunks"
    # create a directory to store the audio chunks
    if not os.path.isdir(folder_name):
        os.mkdir(folder_name)
    whole_text = ""
    # process each chunk 
    for i, audio_chunk in enumerate(chunks, start=1):
        # export audio chunk and save it in
        # the `folder_name` directory.
        chunk_filename = os.path.join(folder_name, f"chunk{i}.wav")
        audio_chunk.export(chunk_filename, format="wav")
        # recognize the chunk
        with sr.AudioFile(chunk_filename) as source:
            audio_listened = r.record(source)
            # try converting it to text
            try:
                text = r.recognize_google(audio_listened)
            except sr.UnknownValueError as e:
                print("Error:", str(e))
            else:
                text = f"{text.capitalize()}. "
                print(chunk_filename, ":", text)
                whole_text += text
    # return the text for all chunks detected
    return whole_text