pyVideoTrans

What is pyVideoTrans

pyVideoTrans is an open source and free AI video translationand dubbing tool designed for multilingual video content creation and distribution. It integrates advanced speech recognition, machine translation and speech synthesis technologies, and supports the automation of the entire process from video speech recognition, subtitle translation to dubbing generation. Users can easily realize cross-language translation and dubbing of videos without professional background, helping content break through language barriers and reach global audiences.

Main functions of pyVideoTrans

1. Fully automated video translation and dubbing
   • Speech Recognition (ASR): Support multiple speech recognition models, such as Faster-Whisper, OpenAI Whisper, etc., to accurately convert speech to text in videos.
   • subtitle translationIt integrates mainstream translation engines such as DeepSeek, ChatGPT, Google Translate, etc., and supports bidirectional translation in 12 input languages and 101 output languages.
   • Speech synthesis (TTS): Provides Edge-TTS, OpenAI TTS, Azure TTS and other speech synthesis engines to generate natural and smooth voiceovers, and supports voice cloning and emotion adjustment.
2. Batch processing and efficient editing
   • Supports batch import of video files, automatically completes the voice recognition, translation and dubbing process, dramatically improves processing efficiency.
   • Provides an interactive editing interface that allows the user to pause and manually proofread at each processing stage to ensure output accuracy.
3. Multi-format support and video compositing
   • Supports common video formats such as MP4, AVI, MOV, and subtitle formats such as SRT, VTT, ASS.
   • Translated subtitles and dubbing can be seamlessly composited into the original video to maintain audio and visual synchronization.
4. Advanced Feature Extensions
   • Intelligent segment processing: For long videos, it supports segmentation by scene or time to avoid memory shortage.
   • Terminology management: Allows users to import specialized terminology dictionaries to ensure accurate translations of specific terms.
   • CUDA Acceleration: Supports NVIDIA graphics acceleration to dramatically increase the speed of speech recognition and video synthesis.
5. Auxiliary tool integration
   • Video/Audio/Subtitle Merge: Supports merging video, audio and subtitle files after processing them independently.
   • Separation of vocals from background sound: Based on the UVR-MDX-NET model, intelligently separates vocals and background music for easy post-editing.
   • Image Watermark Addition: Support batch adding image watermarks to videos to protect intellectual property or enhance brand exposure.

How to use pyVideoTrans?

1. Installation and Configuration
   • Windows user: Download pre-packaged .exe version, unzip it and run it directly sp.exeThe Python environment does not need to be configured.
   • Other platforms (macOS/Linux)::
     • Clone the project code:git clone https://github.com/jianchang512/pyvideotrans.git
     • Go to the project catalog:cd pyvideotrans
     • Install the dependencies:pip install -r requirements.txt(Recommended use of virtual environments to isolate dependencies)
     • Run the program:python pyvideotrans.py
2. Basic Operation Procedure
   • Importing video filesSelect the “Video Translation” function in the main interface and upload the video file you want to translate.
   • Configuring Language Parameters::
     • Select the source language (the original language of the video) and the target language (the language to be translated into).
     • Select a translation engine (e.g. Google Translate, ChatGPT, etc.) and a speech synthesis engine (e.g. Edge-TTS, Azure TTS).
   • Adjusting Recognition Settings(Optional):
     • Enable noise filtering (for videos in noisy environments).
     • Imported terminology dictionaries to ensure accurate translation of specific terms.
   • Starting translation processingClick the “Translate” button, the tool will automatically complete the process of speech recognition, subtitle translation and speech synthesis.
   • Preview and Export: After processing, preview the translation effect and export the video file with the new dubbing after confirming that there is no error.
3. Advanced Function Use
   • batch file: In the file selection screen, press and hold Ctrl key (Windows) or Command key (macOS) to select multiple video files for batch translation and dubbing.
   • segmentationFor long videos, turn on the “Smart Segmentation” function in the settings, the tool will automatically split the video by scene or time, and then merge the videos after processing.
   • voice cloning: In Speech Synthesis Settings, select the “Voice Clone” function and upload a reference audio file to generate a voice over similar to the original.

Recommended Reasons

1. Open source and free of charge, no functional limitations
   • pyVideoTrans based on the GPL-v3 agreement open source , users can use free or Fork modification , do not need to worry about copyright or payment issues .
   • Project created and maintained by the developer “jianchang512” , relying on FFmpeg, PySide6 and other open source projects to build , community support.
2. Multi-language support, covering all major languages of the world
   • Supports 12 input languages and 101 output languages, including Chinese Simplified and Traditional, English, Korean, Japanese, French, German, Spanish and other mainstream languages.
   • Meet the needs of users in different countries and regions, and help globalize the dissemination of content.
3. Advanced technology and high output quality
   • Integrates cutting-edge AI models such as Faster-Whisper, ChatGPT, DeepSeek, etc. to ensure speech recognition accuracy and translation quality.
   • Speech Synthesis supports a wide range of engine and timbre choices to generate natural and smooth voiceovers that remain synchronized with the duration of the original video.
4. Easy to use for non-technical users
   • Provides a graphical interface and interactive editing features that make it easy for users to get started without a programming background.
   • The operation process is intuitive, from video import to export in just a few steps, dramatically improving work efficiency.
5. Flexibility to expand to meet individual needs
   • Support local offline deployment and a variety of mainstream online API calls, users can choose the most suitable program according to demand.
   • Provide rich API interfaces and plug-in extensions, such as ChatTTS interfaces, custom speech recognition models, etc.
6. Active community, continuous update and optimization
   • The project has gained the attention of many developers and users on GitHub, with over 6.5k favorites and active community maintenance.
   • The developer regularly releases updated versions to fix known issues and add new features to ensure the stability and sophistication of the tool.