IBM_Speech_to_Text.py

def audioToText(audioFile):
    """ Converting audio mp3 to text """

    driver.execute_script('''window.open("","_blank")''')
    driver.switch_to.window(driver.window_handles[1])
    driver.get(SpeechToTextURL)

    delay()
    audioInput = driver.find_element(By.XPATH, '//*[@id="root"]/div/input')
    # upload file mp3 to input
    audioInput.send_keys(audioFile)

    time.sleep(audioToTextDelay)
    # waiting for conversion to text

    text = driver.find_element(By.XPATH, '//*[@id="root"]/div/div[7]/div/div/div/span')
    while text is None:
        text = driver.find_element(By.XPATH, '//*[@id="root"]/div/div[7]/div/div/div/span')

    result = text.text  # final text after conversion

    driver.close()
    driver.switch_to.window(driver.window_handles[0])

    return result