Extract Hardsub From Video May 2026

Some hardsubs jump from bottom-center to top-left (e.g., dual-language translations). You cannot use a single ROI. Instead, use full-frame OCR with region detection enabled in tools like Subtitle Edit (check "auto detect subtitle area per frame").

| Scenario | Best Tool | |----------|------------| | Short clip, clean font | Subtitle Edit + Tesseract | | Long movie, batch processing | VideoSubFinder | | Stylized/artistic subs | Manual typing | | One-time small job | Subtitle Edit (trial first) | extract hardsub from video

If you’re comfortable with command-line tools, you can build your own extractor: Some hardsubs jump from bottom-center to top-left (e

# Step 1: Extract frames every second
ffmpeg -i video.mkv -vf fps=1 frame_%04d.png

Export frames or a frame strip


Preprocess images to improve OCR




Run OCR


For better results tune PSM (page segmentation mode) and OEM (engine mode).
For non-Latin languages, install the appropriate language data.


Group recognized text into subtitle cues


Clean and proofread


Export to .srt or .ass



Tips to improve OCR:
Hard subtitles (hardsubs) are burned into the video image and cannot be toggled off. Extracting—or more precisely removing—hardsubs is different from extracting soft subtitles (subtitle files). This post explains options, trade-offs, and step-by-step methods for two common goals: (A) remove hardsubs to produce a “clean” video, and (B) extract subtitle text from hardsubs into an editable subtitle file (OCR). I cover tools, workflows, and practical tips. | Scenario | Best Tool | |----------|------------| |