Timestamped evidence
Each likely match is tied to a transcript timestamp, so reviewers can jump directly to the risky moment instead of scrubbing through the full audio track.
Use case · video profanity filter
Video profanity filter for creator teams that review before export.
Disprofanity helps multilingual creator and production teams flag likely profanity, slurs, risky phrases, and custom words at exact timestamps before publishing monetized clips, podcasts, and short-form batches.
Creator workflow
Review signal checklist
Flag obvious and obscured profanity in transcript context before rendering.
Review slurs, sensitive phrases, sponsor names, and custom hotwords in one workbench.
Choose actions like silence, beep, replace, or review at the timestamp level.
Run extraction, conversion, and media preparation on the FC backend without local device load.
Use non-Whisper long-form speech recognition for audio and video files up to 12 hours.
Use-case fit
Auto-bleep is not enough when creator teams need control.
A video profanity filter should not only mute words automatically. Creator teams need to see what was detected, why it was flagged, where it appears, and what action will be applied before they publish or monetize the clip. Heavy media processing should run in the backend, not on the creator’s device.
Scenario packs
Start from profanity and slur review packs, then add team-specific hotwords for sponsors, talent names, slang, or recurring creator phrases.
Review-before-render
Disprofanity separates detection from final export. Teams review decisions first, save edits, and only then render a cleaned video.
Server-side media processing
Extraction, conversion, and media preparation run on the FC backend, so uploads can continue in the background without relying on the creator’s local CPU, browser tab, or system resources.
Long-form speech recognition
Disprofanity uses a non-Whisper long-form speech recognition architecture, supporting audio and video files up to 12 hours while preserving recognition accuracy.
Workflow
How video profanity cleanup works
Upload media
Send a video, podcast segment, long-form audio file, or short-form content batch.
Process on FC backend
Run extraction, conversion, and media preparation in the backend without local device load.
Recognize long-form speech
Use non-Whisper long-form ASR for audio and video files up to 12 hours.
Review and export
Check timestamped matches, choose actions, and render the final reviewed edit only after decisions are saved.
Comparison
Where Disprofanity fits compared with other cleanup workflows
Basic auto-bleep tools
Useful for obvious curse words, but they often hide the decision process and miss custom vocabulary or context-specific terms.
Manual video editing
Flexible but slow. Reviewers still have to find every risky word manually and keep decisions consistent across batches.
Disprofanity
Combines FC backend media processing, long-form speech recognition, scenario lexicons, timestamped decisions, and review-before-render export.
FAQ
Video profanity filter FAQ
What is a video profanity filter?
A video profanity filter helps identify and remove or replace risky spoken words in video content. Disprofanity focuses on timestamped review so teams can decide what to silence, beep, replace, or keep before export.
Can Disprofanity catch custom words?
Yes. Teams can add custom hotwords such as sponsor names, slang, creator catchphrases, or recurring brand terms so the review workflow reflects their actual content.
Can I upload languages other than English?
Yes. The ASR layer can process multilingual audio depending on recognition quality. Disprofanity's deepest built-in review packs are for English and Chinese scenarios, and teams can add custom lexicons for language- or batch-specific terms.
Does Disprofanity automatically publish edited videos?
No. The workflow is review-before-render: users inspect timestamped matches, save decisions, and then export the cleaned edit.
Does Disprofanity use my computer to process videos?
No. Extraction, conversion, and media preparation run on the FC backend, so uploads can continue in the background without relying on your local CPU, browser tab, or system resources.
Can Disprofanity handle long videos or audio files?
Yes. Disprofanity uses a non-Whisper long-form speech recognition architecture, supporting audio and video files up to 12 hours while preserving recognition accuracy.
Get started
Review risky words before publishing.
Start with a sample clip, choose scenario packs, review timestamped matches, and export only after the decisions are clear.
Create an account