Answers for "python speech to text"

python text to speech

CopyThe 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()

python speech recognition

Copy#pip install SpeechRecognition
#in case of error use 'pip install pyaudio' or...
#in case of error use 'pip install pipwin' then 'pipwin install pyaudio'
#if error continued you may need to use python 3.6 or lower as the latest 
#python may not support pyaudio... 
import speech_recognition as sr
import pyttsx3

#audio of system to respond
engine = pyttsx3.init('sapi5')
voices = engine.getProperty('voices')
engine.setProperty('voice', voices[0].id)
engine.setProperty('rate',180)

def speak(audio):
    engine.say(audio)
    engine.runAndWait()

# simple function to recognise speech from user
def takecommand():
    #it takes microphone input and returns string output
    r = sr.Recognizer()
    with sr.Microphone() as source:
        print('Listening.....')
        r.pause_threshold = 1
        r.energy_threshold = 4000
        audio = r.listen(source)

    try:
        print('Recognising...')
        query = r.recognize_google(audio, language='en-in')
        print('User Said : ' , query)

    except Exception as e:
        print('exception : ',e)

        speak("Sorry, I didn't hear that, Say that again Please")
        return "None"
    return query
while True:
  query = takecommand() # whatever user says will be stored in this variable
  print("The Test got in program is : "+query)

python speech to text

Copyimport 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()

python speech recognition

Copyimport speech_recognition as sr

def take_command():
    r = sr.Recognizer()
    with sr.Microphone() as source:
        print('Listening...')
        r.pause_threshold = 1
        r.energy_threshold = 50
        audio = r.listen(source)

    try:
        print('Recognizing...')
        qry = r.recognize_google(audio, language='en-in')
        print(f"user said: {qry}\n")
        
#     if any error occurs this line will run
    except Exeption as e:
    # if you don't want to print the error comment the bottom line
        print(e)
        print('Say that again please\n')
        return 'None'

    return qry
  
if __name__ == '__main__':
	while True:
  		qry = takecommand().lower()
  
# now you can use the takecommand function where you want to recognize speech
# And please experiment with the above code 
# like what pause_threshold and energy_threshold do 
/\/\/\/\/\/\/\/\/\/\/\---  *HAPPYCODING*  ---/\/\/\/\/\/\/\/\/\/\/\

python code voice to text

Copy# 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

python speech to text

Copypip install pyttsx3