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 は APIMODELS の動画生成 API です。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. APIMODELS のプラットフォーム経由なら、統一 API と明朗な従量課金でこのモデルを呼び出せます。 現在の料金: per second: $0.015。
広告キャンペーンや SNS 施策に向けたブランド動画を短時間で作ります。
TikTok、Instagram、YouTube 向けの縦型ショート動画を量産できます。
機能紹介やチュートリアル動画を作り、コンバージョンにつなげます。
講座の解説、知識の説明、研修用の動画を低コストで継続的に作れます。
Subtitle Eraser は APIMODELS 経由で per second: $0.015 で利用できます。課金は従量制で、生成した分だけの支払いです。
APIMODELS に登録して API キーを取得し、統一エンドポイントを呼ぶだけです。cURL / Python / Node.js のサンプルを含む詳しいドキュメントを用意しています。
APIMODELS は同じ Subtitle Eraser を集約プラットフォーム経由で提供します。統一された API インターフェースなので、プロバイダごとにアカウントを作る必要はありません。キー 1 本ですべてのモデルに届きます。
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.
APIMODELS では Subtitle Eraser が 60 以上のモデルと同じ API キー・同じ残高の上に並んでいるので、選択は「相性」の問題であって「囲い込み」の問題ではありません。Subtitle Removal、Watermark & Logo、On-screen Text、Region Targeting、Time Ranges、$0.015/s に対応しており、他の動画生成モデルと価格・機能を並べて評価できます。乗り換えはモデル名の文字列を 1 つ書き換えるだけ。新しいアカウントも追加の実装も要りません。動画生成の選択肢と最新価格は apimodels.app/models で確認できます。
Subtitle Eraser は次に対応しています: Subtitle Removal、Watermark & Logo、On-screen Text、Region Targeting、Time Ranges、$0.015/s。パラメータの全一覧と呼び出し例は APIMODELS のドキュメントをご覧ください。
はい。APIMODELS は Subtitle Eraser を単一の統一 API とキー 1 本で提供します。プロバイダごとのアカウントも、各社の地域ごとのネットワーク経路を自分で面倒みる必要もありません。
Stripe（Visa、Mastercard などの国際カード）と Alipay に対応しています。支払い後、残高はすぐ反映されます。
How to get access, regional availability, and how this model compares with its alternatives.