---
title: Audio/Video Translation Toolkit
emoji: 🚀
colorFrom: indigo
colorTo: purple
sdk: gradio
python_version: 3.10.0
app_file: app.py
tags:
  - translation
  - audio
  - video
  - speech-synthesis
  - voice-cloning
  - gradio
---

# 🚀 Audio/Video Translation Toolkit

This application provides a complete pipeline for translating the audio of a video or audio file from English to various Indian languages. It handles everything from vocal separation and transcription to translation, speech synthesis, and voice cloning.

---

## ## Key Features 🛠️

* **🎬 Full Video Translation:** Upload a video, and the app will extract the audio, translate it, and merge it back into the original video.
* **🎵 Full Audio Translation:** Translate standalone audio files.
* **🗣️ Vocal Separation:** Isolate vocals from background music before processing.
* **✍️ Transcription & Pace Detection:** Uses Whisper to transcribe the audio and determine the original speaker's pace.
* **🌐 Multi-Lingual Translation:** Translate text to Tamil, Telugu, or Hindi using either local models or the Sarvam API.
* **🔊 Speech Synthesis:** Generate new speech in the target language using models from `ai4bharat`.
* **🧬 Voice Cloning:** Clone the voice from the original speaker onto the newly synthesized audio for a more natural result.

---

## ## How to Use the Main Pipeline

1.  Navigate to the **Translate Video** or **Translate Audio** tab.
2.  Upload your file.
3.  Select the **Target Language**.
4.  Click the **Translate** button and wait for the process to complete.

---