Voice Translator 🔊 using Python Codes:

code: 

import googletrans
import speech_recognition
import gtts
import playsound3
input_lang= "en"
output_lang= "fr"
recognizer = speech_recognition.Recognizer()
with speech_recognition.Microphone() as source:
    print("speak now")
    voice = recognizer.listen(source)
    text = recognizer.recognize_google(voice, language=input_lang)
    print(text)
translator= googletrans.Translator()
translation = translator.translate(text,dest= output_lang)
print(translation.text)
converted_audio= gtts.gTTS(translation.text, lang=output_lang)
converted_audio.save("hello.mp3")
playsound3.playsound("hello.mp3")
#print(googletrans.LANGCODES)

The output of your code is expected to be a translation of the spoken input text from English to French, and then the translated text will be converted to speech and played back. Here is a step-by-step breakdown of the expected output:

1. **Prompt for Speaking**: The code will print "speak now" and wait for you to speak into the microphone.

2. **Capture and Recognize Speech**: The spoken text will be captured and recognized by Google's speech recognition service. This recognized text will be printed.

3. **Translation**: The recognized text will be translated from English (`input_lang="en"`) to French (`output_lang="fr"`) using the `googletrans` library. The translated text will be printed.

4. **Text-to-Speech Conversion**: The translated text will be converted to speech using the `gtts` library and saved as an MP3 file named "hello.mp3".

5. **Play Audio**: The MP3 file will be played using the `playsound3` library.

Here's the revised code to ensure it runs correctly:

```python

import googletrans

import speech_recognition as sr

from gtts import gTTS

import playsound

input_lang = "en"

output_lang = "fr"

recognizer = sr.Recognizer()

with sr.Microphone() as source:

    print("Speak now")

    voice = recognizer.listen(source)

    try:

        text = recognizer.recognize_google(voice, language=input_lang)

        print("You said:", text)

    except sr.UnknownValueError:

        print("Sorry, I did not understand that.")

    except sr.RequestError:

        print("Could not request results from Google Speech Recognition service")

translator = googletrans.Translator()

translation = translator.translate(text, dest=output_lang)

print("Translation:", translation.text)

converted_audio = gTTS(translation.text, lang=output_lang)

converted_audio.save("hello.mp3")

playsound.playsound("hello.mp3")

```

### Expected Output:

1. **Console Output**:

   - "Speak now" (prompt to start speaking).

   - "You said: [recognized text]" (the text recognized by the speech recognition service).

   - "Translation: [translated text]" (the translated text in French).

2. **Audio Output**:

   - The French translation of the spoken English text will be played back.

### Important Note:

Ensure you have the necessary libraries installed:

```bash

pip install googletrans==4.0.0-rc1 SpeechRecognition gtts playsound

```

This setup should work correctly for capturing, translating, and playing back the translated speech.