Convert Speech to Text and Text to Speech in Python using Pyttsx3

Convert Speech to Text and Text to Speech in Python source code

Python is one of the most powerful programming languages available, and it can be used to convert speech to text, and text to speech. This makes it possible to create applications that feature natural language processing (NLP), such as voice recognition and audio search engines. In this blog post we will explore how to use Python to convert speech to text and text to speech.

Speech to Text

One way to convert speech to text is to use an API that uses deep learning models, such as Google’s Cloud Speech-to-Text API. This API allows you to send audio files to a cloud-based speech recognition service, and it returns a text transcription of the audio file. To use this API in Python, you will need to install the relevant packages, such as the Google Cloud Client Library for Python. Once you have the packages installed, you can use the API for speech-to-text conversion.

Text to Speech

To convert text to speech in Python, you will need to install the gTTS (Google Text-to-Speech) library. This library supports multiple languages, so you can easily adjust your application to work with different languages. Once you have the gTTS package installed, you can use it to convert any text string into an MP3 audio file. You can then use the audio file to play the text-to-speech output on your application.

Python code that demonstrates how to convert speech to text and text to speech using the speech_recognition and pyttsx3 libraries:

import speech_recognition as sr
import pyttsx3

# Initialize the recognizer and engine instances
r = sr.Recognizer()
engine = pyttsx3.init()

# Convert speech to text
def speech_to_text():
    with sr.Microphone() as source:
        print("Speak something...")
        audio = r.listen(source)
        try:
            text = r.recognize_google(audio)
            print("You said: ", text)
        except:
            print("Sorry, could not recognize your speech")

# Convert text to speech
def text_to_speech(text):
    engine.say(text)
    engine.runAndWait()

# Call the functions
speech_to_text()
text_to_speech("Hello, how are you?")

In the above code, we first import the speech_recognition and pyttsx3 libraries. We then initialize instances of the Recognizer and Engine classes from these libraries.

We define two functions - speech_to_text() and text_to_speech() - to convert speech to text and text to speech, respectively.

In the speech_to_text() function, we use the with statement to open the microphone as a source of audio. We then use the listen() method of the Recognizer class to capture the audio input from the microphone. We use the recognize_google() method to convert the speech to text using Google's speech recognition API.

In the text_to_speech() function, we use the say() method of the Engine class to convert the input text to speech. We then use the runAndWait() method to play the speech audio.

Finally, we call the two functions to test them. The speech_to_text() function waits for user input from the microphone, converts it to text, and prints it to the console. The text_to_speech() function converts the input text to speech and plays it.

Conclusion

In this article we explored how to use Python to convert speech to text and text to speech. We looked at how to use the Google Cloud Speech-to-Text API for speech-to-text conversion, and we also looked at how to use the gTTS package for text-to-speech conversion. With these two methods, you can create applications that feature natural language processing and make use of speech and text input.