The Future of Video Editing
Transform videos into multilingual masterpieces – easily, quickly and precisely. Translate your videos easily and quickly into over 60 languages with lip-sync and natural voices. Free and Open Source.
Transform videos into multilingual masterpieces – easily, quickly and precisely. Translate your videos easily and quickly into over 60 languages with lip-sync and natural voices. Free and Open Source.
VideoVoice Pro makes your videos understandable in any language with AI-powered speech recognition, translation, and speech synthesis. VideoVoice Pro makes your videos understandable in any language with AI-powered speech recognition, translation, and speech synthesis.
Extract audio from any video and transcribe it using offline Whisper technology. Your data stays private and secure on your device. / Extract audio from any video and transcribe it using offline Whisper technology. Your data stays private and secure on your device.
We use leading translation APIs to translate your text into multiple languages. Our AI understands context for natural, fluent results that preserve your original message. / We use leading translation APIs to translate your text into multiple languages. Our AI understands context for natural, fluent results that preserve your original message.
Forget robotic voices! VideoVoice Pro uses Google Text-to-Speech to generate a new audio track that sounds natural, pleasant, and easy to understand. / Forget robotic voices! VideoVoice Pro uses Google Text-to-Speech to generate a new audio track that sounds natural, pleasant, and easy to understand.
Reach an even wider audience by automatically generating SRT subtitle files in your target language. Perfect for social media, online courses, and more. / Reach an even wider audience by automatically generating SRT subtitle files in your target language. Perfect for social media, online courses, and more.
Leverage the power of Gemini to intelligently summarize long videos. Perfect for presentations, learning content, or marketing videos that need to be concise. / Leverage the power of Gemini to intelligently summarize long videos. Perfect for presentations, learning content, or marketing videos that need to be concise.
Merge the new TTS audio with the original video file to create a translated video. Soon, VideoVoice Pro will allow you to clone your own voice or choose from a library of professionally created voices. / Merge the new TTS audio with the original video file to create a translated video. Soon, VideoVoice Pro will allow you to clone your own voice or choose from a library of professionally created voices.
Simple process to translate your videos and reach a global audience.
Choose your video file directly from your computer (MP4, AVI, MOV etc.)
Using Whisper technology, your video is transcribed locally without sending data online
Choose one or more target languages and optional Gemini summarization
Download your translated videos with Google TTS synchronization and optional subtitles
VideoVoice Pro performs transcription offline with Whisper, connects online to translation and text-to-speech services, and processes everything locally on your machine.
Get started with VideoVoice Pro! Choose between the complete Windows setup for easy installation or the script for manual setup and customization. Both options offer multilingual video translation support and interface languages.
For advanced users: Download the Python script to run VideoVoice Pro manually. Follow the setup guide to install Python, FFmpeg, and requirements.txt. Offers full customization options and multilingual video translation & interface.
Easy installer for Windows with automatic setup. Includes interface language selection during the installation process. Quick start with localized interface!
To run VideoVoice Pro via script, you need to download the script, install Python requirements, and set up FFmpeg. Choose your interface language and run the corresponding script.
Install the necessary Python libraries with pip. Save the following content in a file named 'requirements.txt' and run 'pip install -r requirements.txt'.
# requirements.txt
ffmpeg-python==0.2.0
torch>=2.0.0 # or latest stable version
torchaudio # Required for latest Whisper versions
whisperx # for improved Whisper, if needed
faster-whisper # faster inference, if needed
numpy>=1.24.0
opencv-python>=4.8.0
pydub>=0.25.1
deep-translator>=1.9.0
moviepy>=1.0.3
srt>=3.6.0
gTTS>=2.3.2 # Google Text-to-Speech
google-cloud-translate>=3.11.0
google-generativeai>=0.2.0 # for Gemini summarization
PyQt6>=6.5.0 # for GUI
yt-dlp # for Youtube download, if needed
Download the main Python script and follow these steps to set up FFmpeg and your Python environment.
# 1. Install FFmpeg (Example for Ubuntu/Debian)
sudo apt update && sudo apt install ffmpeg
# 2. Create a virtual environment (recommended)
python3 -m venv venv
# 3. Activate the virtual environment
# - On Windows: venv\\Scripts\\activate
# - On Linux/macOS: source venv/bin/activate
# 4. Install Python Requirements
pip install -r requirements.txt
# 5. Download the Python script (choose your language)
# - For German interface: video_de.py
# - For English interface: video_en.py
# - ... (other languages)
# (Link to download scripts would be here)
# ... or create the script file (e.g., video_en.py) and load the content into it.
# 6. Run the script (Example for English interface)
python video_en.py