Merge pull request #1800 from Shivansh-Jain-github/SJ_PR3

Adding python script to convert audio input to text input.

Author: 1e9abhi1e10

Audio to Text Convertor/README.md

@@ -0,0 +1,21 @@
+# Speech to Text Conversion
+
+This Python script demonstrates how to convert audio input into text using the `speech_recognition` library. It utilizes the `recognize_google` function from the library to convert the speech into text.
+
+## Prerequisites
+- Python 
+- `speech_recognition` library (install using `pip install SpeechRecognition`)
+- `pyaudio` library (install using `pip install pyaudio`)
+
+Note: The `pyaudio` library is required for microphone access and recording audio.
+
+## Usage
+1. Ensure that you have a working microphone connected to your computer.
+2. Run the script and speak into the microphone when prompted.
+3. The script will convert the audio to text using the Google Speech Recognition service.
+4. If the speech is recognized, the converted text will be displayed.
+5. Now, you can do whatever operations you want with the input text.
+
+
+
+Feel free to use this code as a starting point for your speech-to-text conversion tasks.

Audio to Text Convertor/code.py

@@ -0,0 +1,37 @@
+import speech_recognition as sr
+
+def convert_audio_to_text():
+    # Initialize the recognizer
+    r = sr.Recognizer()
+
+    # Open the microphone and start recording
+    with sr.Microphone() as source:
+        print("Speak something...")
+        audio = r.listen(source)  # Record audio from the microphone
+
+    try:
+        # Use the recognizer to convert audio to text
+        text = r.recognize_google(audio)  # Convert audio to text using Google Speech Recognition service
+        return text
+    except sr.UnknownValueError:
+        print("Unable to recognize speech.")  # Handle the case when speech cannot be recognized
+    except sr.RequestError as e:
+        print("Error: {0}".format(e))  # Handle any errors that occur during speech recognition
+
+# Example usage
+audio_text = convert_audio_to_text()  # Call the function to convert audio to text
+if audio_text:
+    print("You said:", audio_text)  # Print the converted text
+
+# Manipulate the text for further operations
+if audio_text:
+    # Convert the text to lowercase
+    lowercase_text = audio_text.lower()
+    print("Lowercase text:", lowercase_text)
+
+    # Split the text into words
+    words = lowercase_text.split()
+    print("Words:", words)
+
+    # Perform other operations on the text as needed
+