Automate bilingual subtitle creation from video with karaoke support.
npx skills add https://github.com/vorojar/bilingual-subtitle-skill --skill -vorojar
Please help me install this Agent Skill. Skill: 双语字幕生成 Source: https://github.com/vorojar/bilingual-subtitle-skill/tree/main Command: npx skills add https://github.com/vorojar/bilingual-subtitle-skill --skill -vorojar
This Skill automates the time-consuming process of generating bilingual subtitles from video sources, including translation and optional karaoke highlighting, saving hours of manual work.
Run the bilingual subtitle generator on a sample video to produce subtitles.
High-intent search queries and answers about installing and using this skill.
To generate bilingual subtitles automatically, this Skill extracts audio from the video, transcribes it using Whisper, translates the text, and embeds the bilingual output using FFmpeg.
Yes, you can create karaoke style subtitles. This Skill supports karaoke highlighting and allows you to adjust fonts and margins before embedding the subtitles into the video.
Yes, the bilingual subtitle generator supports hardware-accelerated backends. It utilizes faster-whisper and mlx-whisper to accelerate the transcription process during subtitle generation.
Available output formats include bilingual, source-only, and translated-only subtitles. These can be produced as standalone files or embedded directly into the video using FFmpeg encoding.
Yes, FFmpeg is required for embedding subtitles. It handles the video encoding process to produce ready-to-use video files with the translated bilingual, source-only, or karaoke subtitles embedded.
The best way to localize video content is automating the end-to-end workflow. This Skill extracts audio, transcribes speech, translates text, and embeds bilingual subtitles for multilingual audiences.
xingBaGanAnalyze video content and transcribe audio locally with ffmpeg and Whisper.
binnu-devDownload videos, generate Korean/English subtitles, and burn them with ffmpeg.
martinholovskyTranscribe audio files locally with Faster Whisper speech-to-text.
MarbleSodasTranscribe and translate spoken audio into text with timestamps.
