Language Translator Using Python

Last Updated : 18 Apr, 2026

A language translator is a tool that converts text or speech from one language to another, helping people understand and communicate in different languages. In this tutorial, we will build a Voice-based Language Translator in Python

The translator will: 

  • Take your speech input in one language
  • Translate it to another language
  • Convert the translated text into speech

Libraries Installation

We will use the following Python libraries:

  • googletrans: To translate text
  • SpeechRecognition: To capture and recognize speech
  • PyAudio: To use the microphone
  • gTTS: To convert text into speech

Install the libraries using pip:

pip install googletrans
pip install SpeechRecognition
pip install PyAudio
pip install gTTS

Note: Installing PyAudio on Windows may require portaudio setup

Voice Translator

The following Python code captures your speech, translates it to another language, and plays the translated audio.

Python 
import speech_recognition as sr
from googletrans import Translator
from gtts import gTTS
import os

recog = sr.Recognizer()
mic = sr.Microphone()

def recognize_speech(recog, source):
    try:
        recog.adjust_for_ambient_noise(source, duration=0.2)  
        audio = recog.listen(source)  
        text = recog.recognize_google(audio)  
        return text.lower()
    except sr.UnknownValueError:
        print("Could not understand the audio.")
        return None
    except sr.RequestError as e:
        print(f"Error from Google Speech Recognition service; {e}")
        return None

with mic as source:
    print("Speak 'hello' to start the translation!")
    user_input = recognize_speech(recog, source)

if user_input and 'hello' in user_input:
    translator = Translator()
    
    from_lang = 'en'  
    to_lang = 'hi'    
    
    with mic as source:
        print("Speak a sentence to translate...")
        sentence = recognize_speech(recog, source)
        
        if sentence:
            try:
                print(f"Phrase to be Translated: {sentence}")
                translated_text = translator.translate(sentence, src=from_lang, dest=to_lang).text
                print(f"Translated Text: {translated_text}")
                
                speech = gTTS(text=translated_text, lang=to_lang, slow=False)
                speech.save("translated_voice.mp3")
                
                os.system("start translated_voice.mp3")
            
            except Exception as e:
                print(f"An error occurred: {e}")
        else:
            print("Could not capture the sentence.")

Output

Speak 'hello' to start the translation!
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Speak a sentence to translate...
Phrase to be Translated: What are you doing
Translated Text: आप क्या कर रहे हैं

Explanation:

  • recog = sr.Recognizer() & mic = sr.Microphone(): Initializes recognizer and microphone objects.
  • recognize_speech(recog, source): Captures audio, adjusts for ambient noise, converts it to text, handles errors (UnknownValueError and RequestError).
  • with mic as source: Opens the microphone for input and prompts the user to say “hello”.
  • user_input = recognize_speech(recog, source): Captures and stores the trigger word.
  • translator = Translator(): Initializes Google Translator object.
  • sentence = recognize_speech(recog, source): Captures the sentence to translate.
  • translated_text = translator.translate(sentence, src=from_lang, dest=to_lang).text: Translates the captured text.
  • speech = gTTS(...) & speech.save(...): Converts translated text to speech and saves it as an MP3 file.
  • os.system("start translated_voice.mp3"): Plays the generated audio automatically.
Comment

Explore