Create a real time voice translator using Python

In this article, we are going to create a real-time voice translator in Python.

Module needed

• playsound: This module is used to play sound in Python

pip install playsound

• Speech Recognition Module: It is a library with the help of which Python can recognize the command given. We have to use pip for Speech Recognition.

pip install SpeechRecognition

• googletrans: Googletrans is a free and unlimited python library that implemented Google Translate API

pip install googletrans

• gTTs: The gTTS API supports several languages including English, Hindi, Tamil, French, German and many more. 

pip install gTTs
pip install gTTS-token

A real-time voice translator that can translate voice input and give translated voice output generated from it. It is created using google’s googleTrans API and speech_recognition library of python. It converts text from one language to another language and saves its mp3 recorded file. The playsound module is then used to play the generated mp3 file, After that, the generated mp3 file is deleted using the os module.

Stepwise implementation

Step 1: Importing Necessary Modules

Python3

# Importing necessary modules required
from playsound import playsound
import speech_recognition as sr
from googletrans import Translator
from gtts import gTTS
import os

Step 2: A tuple of all the languages mapped with their code

Python3

dic=('afrikaans', 'af', 'albanian', 'sq', 'amharic', 'am',
     'arabic', 'ar', 'armenian', 'hy', 'azerbaijani', 'az',
 'basque', 'eu', 'belarusian', 'be', 'bengali', 'bn', 'bosnian',
     'bs', 'bulgarian', 'bg', 'catalan', 'ca',
  'cebuano', 'ceb', 'chichewa', 'ny', 'chinese (simplified)',
     'zh-cn', 'chinese (traditional)', 'zh-tw',
  'corsican', 'co', 'croatian', 'hr', 'czech', 'cs', 'danish',
     'da', 'dutch', 'nl', 'english', 'en', 'esperanto',
  'eo', 'estonian', 'et', 'filipino', 'tl', 'finnish', 'fi',
     'french', 'fr', 'frisian', 'fy', 'galician', 'gl',
  'georgian', 'ka', 'german', 'de', 'greek', 'el', 'gujarati',
     'gu', 'haitian creole', 'ht', 'hausa', 'ha',
  'hawaiian', 'haw', 'hebrew', 'he', 'hindi', 'hi', 'hmong',
     'hmn', 'hungarian', 'hu', 'icelandic', 'is', 'igbo',
  'ig', 'indonesian', 'id', 'irish', 'ga', 'italian', 'it',
     'japanese', 'ja', 'javanese', 'jw', 'kannada', 'kn',
  'kazakh', 'kk', 'khmer', 'km', 'korean', 'ko', 'kurdish (kurmanji)',
     'ku', 'kyrgyz', 'ky', 'lao', 'lo',
  'latin', 'la', 'latvian', 'lv', 'lithuanian', 'lt', 'luxembourgish',
     'lb', 'macedonian', 'mk', 'malagasy',
  'mg', 'malay', 'ms', 'malayalam', 'ml', 'maltese', 'mt', 'maori',
     'mi', 'marathi', 'mr', 'mongolian', 'mn',
  'myanmar (burmese)', 'my', 'nepali', 'ne', 'norwegian', 'no',
     'odia', 'or', 'pashto', 'ps', 'persian',
   'fa', 'polish', 'pl', 'portuguese', 'pt', 'punjabi', 'pa',
     'romanian', 'ro', 'russian', 'ru', 'samoan',
   'sm', 'scots gaelic', 'gd', 'serbian', 'sr', 'sesotho',
     'st', 'shona', 'sn', 'sindhi', 'sd', 'sinhala',
   'si', 'slovak', 'sk', 'slovenian', 'sl', 'somali', 'so',
     'spanish', 'es', 'sundanese', 'su',
  'swahili', 'sw', 'swedish', 'sv', 'tajik', 'tg', 'tamil',
     'ta', 'telugu', 'te', 'thai', 'th', 'turkish', 'tr',
  'ukrainian', 'uk', 'urdu', 'ur', 'uyghur', 'ug', 'uzbek',
     'uz', 'vietnamese', 'vi', 'welsh', 'cy', 'xhosa', 'xh',
  'yiddish', 'yi', 'yoruba', 'yo', 'zulu', 'zu')

Step 3: Taking voice commands from the user

Python3

# Capture Voice
# takes command through microphone
def takecommand():
    r = sr.Recognizer()
    with sr.Microphone() as source:
        print("listening.....")
        r.pause_threshold = 1
        audio = r.listen(source)

    try:
        print("Recognizing.....")
        query = r.recognize_google(audio, language='en-in')
        print(f"user said {query}\n")
    except Exception as e:
        print("say that again please.....")
        return "None"
    return query

Step 4: Taking voice input from the user

Python3

# Taking voice input from the user
query = takecommand()
while (query == "None"):
    query = takecommand()

Step 5: Input destination language from the user, Mapping user input with the language code

Python3

def destination_language():
    print("Enter the language in which you want to convert \
    : Ex. Hindi , English , etc.")
    print()

    # Input destination language in which the user
    # wants to translate
    to_lang = takecommand()
    while (to_lang == "None"):
        to_lang = takecommand()
    to_lang = to_lang.lower()
    return to_lang

to_lang = destination_language()

# Mapping it with the code
while (to_lang not in dic):
    print("Language in which you are trying to convert\
    is currently not available ,please input some other language")
    print()
    to_lang = destination_language()

to_lang = dic[dic.index(to_lang)+1]

Step 6: Invoking Translator

Python3

# invoking Translator
translator = Translator()

Step 7: Translating from src to dest

Python3

# Translating from src to dest
text_to_translate = translator.translate(query, dest=to_lang)
text = text_to_translate.text

Step 8: Saving Translated files and deleting them after playing

Python3

# Using Google-Text-to-Speech ie, gTTS() method
# to speak the translated text into the
# destination language which is stored in to_lang.
# Also, we have given 3rd argument as False because
# by default it speaks very slowly
speak = gTTS(text=text, lang=to_lang, slow=False)

# Using save() method to save the translated
# speech in capture_voice.mp3
speak.save("captured_voice.mp3")

# Using OS module to run the translated voice.
playsound('captured_voice.mp3')
os.remove('captured_voice.mp3')
print(text)

Below is the full implementation:

Python3

# Importing necessary modules required
from playsound import playsound
import speech_recognition as sr
from googletrans import Translator
from gtts import gTTS
import os
flag = 0

# A tuple containing all the language and
# codes of the language will be detcted
dic = ('afrikaans', 'af', 'albanian', 'sq',
       'amharic', 'am', 'arabic', 'ar',
       'armenian', 'hy', 'azerbaijani', 'az',
       'basque', 'eu', 'belarusian', 'be',
       'bengali', 'bn', 'bosnian', 'bs', 'bulgarian',
       'bg', 'catalan', 'ca', 'cebuano',
       'ceb', 'chichewa', 'ny', 'chinese (simplified)',
       'zh-cn', 'chinese (traditional)',
       'zh-tw', 'corsican', 'co', 'croatian', 'hr',
       'czech', 'cs', 'danish', 'da', 'dutch',
       'nl', 'english', 'en', 'esperanto', 'eo',
       'estonian', 'et', 'filipino', 'tl', 'finnish',
       'fi', 'french', 'fr', 'frisian', 'fy', 'galician',
       'gl', 'georgian', 'ka', 'german',
       'de', 'greek', 'el', 'gujarati', 'gu',
       'haitian creole', 'ht', 'hausa', 'ha',
       'hawaiian', 'haw', 'hebrew', 'he', 'hindi',
       'hi', 'hmong', 'hmn', 'hungarian',
       'hu', 'icelandic', 'is', 'igbo', 'ig', 'indonesian',
       'id', 'irish', 'ga', 'italian',
       'it', 'japanese', 'ja', 'javanese', 'jw',
       'kannada', 'kn', 'kazakh', 'kk', 'khmer',
       'km', 'korean', 'ko', 'kurdish (kurmanji)',
       'ku', 'kyrgyz', 'ky', 'lao', 'lo',
       'latin', 'la', 'latvian', 'lv', 'lithuanian',
       'lt', 'luxembourgish', 'lb',
       'macedonian', 'mk', 'malagasy', 'mg', 'malay',
       'ms', 'malayalam', 'ml', 'maltese',
       'mt', 'maori', 'mi', 'marathi', 'mr', 'mongolian',
       'mn', 'myanmar (burmese)', 'my',
       'nepali', 'ne', 'norwegian', 'no', 'odia', 'or',
       'pashto', 'ps', 'persian', 'fa',
       'polish', 'pl', 'portuguese', 'pt', 'punjabi',
       'pa', 'romanian', 'ro', 'russian',
       'ru', 'samoan', 'sm', 'scots gaelic', 'gd',
       'serbian', 'sr', 'sesotho', 'st',
       'shona', 'sn', 'sindhi', 'sd', 'sinhala', 'si',
       'slovak', 'sk', 'slovenian', 'sl',
       'somali', 'so', 'spanish', 'es', 'sundanese',
       'su', 'swahili', 'sw', 'swedish',
       'sv', 'tajik', 'tg', 'tamil', 'ta', 'telugu',
       'te', 'thai', 'th', 'turkish',
       'tr', 'ukrainian', 'uk', 'urdu', 'ur', 'uyghur',
       'ug', 'uzbek',  'uz',
       'vietnamese', 'vi', 'welsh', 'cy', 'xhosa', 'xh',
       'yiddish', 'yi', 'yoruba',
       'yo', 'zulu', 'zu')


# Capture Voice
# takes command through microphone
def takecommand():
    r = sr.Recognizer()
    with sr.Microphone() as source:
        print("listening.....")
        r.pause_threshold = 1
        audio = r.listen(source)

    try:
        print("Recognizing.....")
        query = r.recognize_google(audio, language='en-in')
        print(f"The User said {query}\n")
    except Exception as e:
        print("say that again please.....")
        return "None"
    return query


# Input from user
# Make input to lowercase
query = takecommand()
while (query == "None"):
    query = takecommand()


def destination_language():
    print("Enter the language in which you\
    want to convert : Ex. Hindi , English , etc.")
    print()

    # Input destination language in
    # which the user wants to translate
    to_lang = takecommand()
    while (to_lang == "None"):
        to_lang = takecommand()
    to_lang = to_lang.lower()
    return to_lang

to_lang = destination_language()

# Mapping it with the code
while (to_lang not in dic):
    print("Language in which you are trying\
    to convert is currently not available ,\
    please input some other language")
    print()
    to_lang = destination_language()

to_lang = dic[dic.index(to_lang)+1]


# invoking Translator
translator = Translator()


# Translating from src to dest
text_to_translate = translator.translate(query, dest=to_lang)

text = text_to_translate.text

# Using Google-Text-to-Speech ie, gTTS() method
# to speak the translated text into the
# destination language which is stored in to_lang.
# Also, we have given 3rd argument as False because
# by default it speaks very slowly
speak = gTTS(text=text, lang=to_lang, slow=False)

# Using save() method to save the translated
# speech in capture_voice.mp3
speak.save("captured_voice.mp3")

# Using OS module to run the translated voice.
playsound('captured_voice.mp3')
os.remove('captured_voice.mp3')

# Printing Output
print(text)

Output: