Audio to Text using Python

import speech_recognition as sr

recognizer = sr.Recognizer()

audio_file = "audiobook.wav"

from pydub import AudioSegment
AudioSegment.from_mp3(audio_file).export(audio_file , format="wav")

with sr.AudioFile(audio_file) as source:
    audio_data = recognizer.record(source)

try:
    text = recognizer.recognize_google(audio_data)
    print("Extracted Text:", text)
except sr.UnknownValueError:
    print("Could not understand the audio.")
except sr.RequestError as e:
    print("API Error:", e)

This code demonstrates how to convert an audio file (specifically an MP3) to WAV format using the pydub library, then transcribe its speech content into text using the speech_recognition library with Google Speech Recognition API. Here's a step-by-step explanation:

1. Importing Libraries

import speech_recognition as sr
from pydub import AudioSegment

• speech_recognition: Used for speech-to-text conversion.
• pydub: A library for processing audio files, including format conversions.

2. Creating a Recognizer

recognizer = sr.Recognizer()

• Creates a Recognizer object, which is used for processing audio and converting it to text.

3. Setting Up the Audio File