video-subtitle-master - an open-source AI subtitle generation tool that supports batch subtitle generation for videos or audio.

What is video-subtitle-master?

video-subtitle-master is a tool for batch generating subtitles for videos or audio files. Developed based on the open-source project VideoSubtitleGenerator, it supports batch subtitle generation for videos or audio files and translation of the subtitles into other languages. video-subtitle-master features a user-friendly graphical interface, supports various translation services (such as Baidu Translate, Volcano Translate, DeepLX, etc.), and integrates whisper.cpp and fluent-ffmpeg for optimized performance. video-subtitle-master allows customization of subtitle filenames, translation content formats, and the number of concurrent tasks, making it suitable for both general users and developers.

The main functions of video-subtitle-master

• Batch processing:
  • Supports batch generation of subtitles for videos or audio.
  • Supports batch translation of subtitle files.
• Subtitle Translation:
  • It supports translating generated or imported subtitles into other languages.
  • It supports a variety of translation services, including Baidu Translate, Volcano Engine Translation, DeepLX, Ollam native models, OpenAI-style APIs, etc.
• Optimization and Integration:
  • The whisper.cpp utility is integrated and optimized for Apple Silicon, improving build speed.
  • It integrates fluent-ffmpeg, eliminating the need to install ffmpeg separately.
  • It supports running locally installed whisper commands.
• Customization features:
  • It supports custom subtitle file names, making it compatible with different media players.
  • It supports customizing the content of the translated subtitle file, allowing you to choose between pure translation or original subtitles plus translation.
  • Supports selecting the model download source (domestic mirror source or official source).
  • Supports customizable number of concurrent tasks.

The technical principles of video-subtitle-master

• Speech recognition technologyUse whisper.cpp or other speech recognition engines to extract text from audio. whisper.cpp is a deep learning-based speech recognition model that can efficiently convert speech into text.
• Subtitle generationText content generated by a speech recognition engine is formatted into a subtitle file (such as SRT or ASS format) according to timestamps.
• Translation service integrationIt supports multiple translation services, translating subtitles into the target language by calling external APIs (such as Baidu Translate, Volcano Engine Translate) or local models (such as Ollama).
• Graphical User Interface (GUI)Developed using modern front-end technologies (such as Electron), it provides an intuitive user interface for easy user operation.
• Backend processingUse Node.js and backend technologies to handle logic such as file reading, model loading, and task scheduling.

The project address for video-subtitle-master

• GitHub repository:https://github.com/buxuku/video-subtitle-master

Application scenarios of video-subtitle-master

• Video creation and publishingIt helps creators quickly generate and translate subtitles, increasing the reach of their content.
• EducationAdd subtitles to instructional videos to aid learning, especially for foreign language learners and students with hearing impairments.
• Content localizationTranslate video subtitles into multiple languages to meet the needs of different regions.
• Personal EntertainmentLe: Generates and translates subtitles for movies, TV series, etc., to enhance the viewing experience.
• Meeting minutesGenerate subtitles for meeting or event videos for easy organization and review.