YuzuLingo vs Extract-Subtitles-by-OCR (JollyToday)
YuzuLingo covers burned-in subtitles on the video you are already watching, including YouTube, Bilibili, and other web players. You do not upload the video, and you do not download it. Turn on Interact to read the burned-in line on your device, with furigana or pinyin when the language has them, and a transcript of the lines in that session. Show that text always, on hover, or while you hold a hotkey.
Extract-Subtitles-by-OCR is JollyToday’s repo on GitHub. The repo says it is the product write-up for Weydub, the international name for GhostCut, not a tool you run from the code. You upload a video, mark the subtitle area, wait, and download an SRT. They also translate that file. They say the service covers 30+ languages and uses Gemini or GPT to proofread the extracted text.
GitHub - JollyToday/Extract-Subtitles-by-OCR: Use OCR technology to extract video hard subtitles, automatically merge multi-line subtitles, add large model auto-calibration. Ultra-high accuracy with no omissions.使用OCR技术提取视频字幕，用大模型自动校准，超高准确率。Where each one fits
| Feature | YuzuLingo | Extract Subtitles by OCR |
|---|---|---|
| No video file to upload or download | ||
| Cover burned-in subs on YouTube, Bilibili, and other web players | ||
| Read that line while the video plays, on your device | ||
| Furigana or pinyin on that line | ||
| A transcript of the lines in that session | ||
| Show that text always, on hover, or while you hold a hotkey | ||
| Turn burned-in subs in an uploaded video into an SRT file | ||
| Translate that file into another language | ||
| Proofread the extracted text with Gemini or GPT | ||
| Add the line to an Anki deck |