Voice Translator is a Python project that transcribes, translates, and converts .wav audio files into spoken text. It uses several libraries, including speech_recognition for transcription, googletrans for translation, and gtts for text-to-speech conversion.
To run this project, you will need Python 3.6 or higher. You will also need several Python libraries, which are listed in the requirements.txt file.
pip install -r requirements.txtAdditionally, this project uses pydub to handle audio files, which requires ffmpeg. Therefore, you need to download ffmpeg and place it in the root of your project.
FFMPEG
- Clone this repository to your local machine.
- Navigate to the project directory in your terminal.
- Install the necessary dependencies.
- Download ffmpeg.
- Unzip the downloaded file and place the ffmpeg folder in the root of your project.
To use this project, place a .wav file in the project directory, then run the voice_translator.py script with the following command:python voice_translator.py
The script will prompt you to choose the source language of the audio and the language you want to translate the text into. It will then transcribe the audio, translate the text, and convert the translated text into spoken audio. The translated audio will be saved in a .mp3 file.
During the language selection process, you can enter '0' to go back to the previous step.