https://github.com/thee-unruly/ai-powered-video-translation-convert-speech-while-retaining-original-voice
This script extracts audio, transcribes it, translates it into multiple languages chosen, generates speech, and merges it back into the video.
https://github.com/thee-unruly/ai-powered-video-translation-convert-speech-while-retaining-original-voice
Last synced: 3 months ago
JSON representation
This script extracts audio, transcribes it, translates it into multiple languages chosen, generates speech, and merges it back into the video.
- Host: GitHub
- URL: https://github.com/thee-unruly/ai-powered-video-translation-convert-speech-while-retaining-original-voice
- Owner: Thee-Unruly
- Created: 2025-03-06T09:17:17.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2025-03-18T06:59:26.000Z (3 months ago)
- Last Synced: 2025-03-18T07:39:45.334Z (3 months ago)
- Language: Python
- Homepage:
- Size: 7.81 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🎥 AI-Powered Video Translation 🎙️🔁🇮🇳
## 📌 Overview
This project enables **automatic speech translation** from any language to **Hindi** while preserving the original speaker’s voice. It processes a **video**, extracts the **audio**, translates the speech, and **generates a new video** with the translated audio while keeping the original tone and style.
## 🚀 Features
✅ **Speech Recognition:** Detects spoken language in the video
✅ **Language Translation:** Converts speech to **Hindi**
✅ **Voice Cloning:** Maintains the speaker's original voice
✅ **Video Processing:** Outputs a new video with the translated audio
## 🛠️ Technologies Used
- 🎤 **Whisper** (for speech recognition)
- 🌍 **OpenAI / Google Translate API** (for translation)
- 🗣️ **ElevenLabs / Coqui TTS** (for voice cloning)
- 🎥 **FFmpeg** (for video/audio processing)