subtitle-eraseSubtitle Eraser removes hardcoded (burned-in) subtitles, on-screen text, watermarks and corner logos from a video and rebuilds a clean background where they used to be. It uses high-frame-rate OCR plus AIGC inpainting (with temporal, multi-frame consistency) to repair each frame, so the result blends in almost invisibly. There are two ways to say what should go. In automatic mode it finds the text for you — choose subtitle mode (default, caption-style subtitles) or text mode (any on-screen text). In region mode you draw the boxes yourself and it works on those instead, which is how you remove a watermark, a station bug or a signature that OCR would never classify as a subtitle. Draw region boxes generously, roughly 30-50% larger than the mark itself: a box cropped tight to the mark often returns the video unchanged, while the same mark with margin around it is removed cleanly. Both modes also accept time ranges, so you can clean only part of the timeline. Output resolution matches the input (capped at 1080p). Billed at $0.015 per second of the video.
Erases burned-in subtitles and rebuilds a clean background where the text used to be
Remove caption-style subtitles only, or any on-screen text anywhere in the frame
Optionally pass normalized (0-1) boxes to erase text only inside the areas you choose
Multi-frame consistent repair for near-invisible results, billed $0.015 per second of video
Upload the video to clean (MP4 / MOV, max 100MB). Billed $0.015 per second.
Finds the text for you. Boxes below are optional and only narrow where it may look.
Caption-style subtitles only. Output resolution matches the input (up to 1080p).
Generated video will appear here
Provide URLs and click Generate
Subtitle Eraser is a Video Generation API provided by APIMODELS. Subtitle Eraser removes hardcoded (burned-in) subtitles, on-screen text, watermarks and corner logos from a video and rebuilds a clean background where they used to be. It uses high-frame-rate OCR plus AIGC inpainting (with temporal, multi-frame consistency) to repair each frame, so the result blends in almost invisibly. There are two ways to say what should go. In automatic mode it finds the text for you — choose subtitle mode (default, caption-style subtitles) or text mode (any on-screen text). In region mode you draw the boxes yourself and it works on those instead, which is how you remove a watermark, a station bug or a signature that OCR would never classify as a subtitle. Draw region boxes generously, roughly 30-50% larger than the mark itself: a box cropped tight to the mark often returns the video unchanged, while the same mark with margin around it is removed cleanly. Both modes also accept time ranges, so you can clean only part of the timeline. Output resolution matches the input (capped at 1080p). Billed at $0.015 per second of the video. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: per second: $0.015.
Quickly generate brand promotion videos for ad campaigns and social media marketing.
Create compelling short-form video content for platforms like TikTok, Instagram, and YouTube.
Generate product feature demonstrations and tutorials to improve user conversion.
Produce course explanations, knowledge explainers, and training videos at low cost.
Subtitle Eraser is available through APIMODELS at: per second: $0.015. Billing is pay-as-you-go — you only pay for what you generate.
Sign up at APIMODELS, get your API key, and call our unified API endpoint. We provide detailed API documentation with code examples in cURL, Python, and Node.js.
APIMODELS offers the same Subtitle Eraser model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.
It removes hardcoded (burned-in) subtitles and on-screen text from a video and rebuilds a clean background where the text used to be. Upload one video and choose subtitle mode (default — removes caption-style subtitles) or text mode (removes other on-screen text, with optional region targeting).
Per second of video ($0.015/s); failed tasks are not charged. Output resolution matches the input (up to 1080p). Ideal for cleaning subtitles off a clip before re-editing or localization.
On APIMODELS, Subtitle Eraser runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Subtitle Removal, Watermark & Logo, On-screen Text, Region Targeting, Time Ranges, $0.015/s, and you can weigh it on price and capability against other Video Generation models, then switch by changing a single model-name string — no new account or integration. Browse every Video Generation option with live pricing at apimodels.app/models.
Subtitle Eraser supports: Subtitle Removal, Watermark & Logo, On-screen Text, Region Targeting, Time Ranges, $0.015/s. See the APIMODELS docs for full parameters and call examples.
Yes. APIMODELS exposes Subtitle Eraser through a single unified API and one key — no separate provider accounts, and no need to handle each provider's regional network access yourself.
We support Stripe (Visa, Mastercard, and other international cards) and Alipay. Credits are available instantly after payment.
How to get access, regional availability, and how this model compares with its alternatives.