Building a Gradio Voice-to-Voice Translator App Without API Keys - Source Code

This source code outlines the implementation of a voice translation app using Gradio, WhisperModel from the faster_whisper library, Google's Text-to-Speech (gTTS) library, and the translate library.

The app allows users to transcribe spoken audio, translate the transcribed text into multiple languages, and convert the translations back into speech.

It provides a user-friendly interface to facilitate seamless multilingual communication.

Files Included:

• main.py: This is the main script that contains the implementation of the voice translation app. It includes functions for transcription, translation, and speech synthesis, and sets up the Gradio interface.

• requirements.txt: A text file listing all the dependencies required to run the app.