Skip to workspace
PixelOkay
Local-first editorVideo toolsHelp
Tools
CREATOR STUDIO • SHORT-FORM VIDEO

Video Repurposer

Find visual moments, customize clips and captions, and export individual or multiple videos in your browser—with no AI required.

4 aspect ratios180s max clip100% local edits
✓ No AI · Local Video EditorManual clips, visual signals, captions and video exports work without model downloads. AI transcription and writing assistance are entirely optional.

Live preview

9:16 Vertical540 × 960
00:0000:00

Keyboard: Space plays/pauses, I sets clip in, O sets clip out, Ctrl/Cmd+Z undo, Ctrl/Cmd+Y redo (when not editing a field).

No AI · Local Video Editor. Load a video to begin.

Export studio

Exports record in real time · No AI needed
WebM where supported; MP4 only if the browser supports native recording. Exports include the source audio where browser media routing supports it.

Made for creators. Designed for control.

1 · Discover

Sample visual changes and motion to find promising parts of a lecture, vlog, stream, or interview. Inspect the suggestions before choosing.

2 · Make it yours

Adjust the cut, manually place the subject, choose the format, import subtitles or create editable captions with optional Whisper speech recognition.

3 · Export locally

Create a video with burned-in captions and source sound. Download caption tracks separately, save your edit decisions, and protect your original file.

Privacy: Videos are processed in this browser. Optional AI transcription downloads open-source model files and runs inference on your device. No upload endpoint, account, or paid API is used. Verify rights to any footage and music you publish.

Using Video Repurposer

Import footage or a demo, select a clip, review framing/path and caption layout, optionally request transcription, then export one clip or render an actual multi-clip queue, and save selections.

Motion-follow is not face/identity tracking or semantic video understanding. Whisper requires external model/runtime downloads and is unverified. Queue can render selected clips sequentially as separate local video files, within a four-minute total batch limit. Clips are 0.6–180 seconds; real-time native recording/codecs/audio vary. Projects omit video.

Related tools

LOCAL AI SETUP

Set up AI on this device

First, a model needs to be loaded on your device

Optional short-form writing assistance uses a WebGPU language model locally. On first use, its files may require a large download. The writing model sees only selected clip timings, optional captions and text metadata, not the video frames, audio or the video file.

  1. 1. Check device
  2. 2. Download / cache
  3. 3. Prepare clip assistant
  4. 4. Suggest repurposing ideas

Device & model resources

Measurements may be approximate
Device RAM / model memoryChecking device information…

Live system RAM, model RAM and GPU memory are not reliably exposed in browsers.

Browser website storageChecking storage…

Site-wide estimate; includes other PixelOkay tools and is not RAM.

ONE ACTION · ALL RECOGNIZED AI MODEL DOWNLOADS

Free AI model storage across PixelOkay

Scan this website origin for WebLLM and Transformers.js model caches, plus recognizable model files in other cache buckets. This includes caches from other PixelOkay tools, not only this tool. No site data or browser databases are cleared automatically.

Run a scan to see how many model caches can be cleared together.

Browser-native models and unknown IndexedDB/OPFS or private runtime caches may remain. Unknown application/user storage will not be deleted. Other running tools might redownload caches; close their tabs first.

Speech transcription — separate local AI

Whisper tiny English (Transformers.js) is used only for the existing AI transcribe clip feature. It needs a video, a selected clip of at most 60 seconds, browser audio capture and potentially a first-use model download. Its files and lifecycle are separate from the text model above. Browser cache reuse cannot be assumed between them.

Transcription starts only after you select this action.

Having trouble downloading or loading AI?

Old or incomplete AI model downloads may be using your browser's storage. First refresh the storage meter or try a smaller model. If setup still fails, inspect and remove recognized AI model caches with confirmation, then download again.

Only model caches are targeted. Other PixelOkay tools may need to redownload their models. Never clear all website data without exporting important chats and projects first.

Select “Check device” to see whether the current model can run.
This model is for text-based clip suggestions. Whisper speech transcription is a separate opt-in model and is never loaded by choosing a text model.
CROSS-TOOL MODEL CACHE CLEANUP

Delete all recognized AI model downloads?

Deleting these caches will cause other PixelOkay tools to download their models again. Loaded AI sessions in other tabs may be disrupted. Unidentified model caches and browser-managed models may remain.

Data-loss caution: This action does not intentionally delete saved chats, projects, drafts, localStorage or IndexedDB. Do not clear website data unless you have backed up work; clearing all website data may permanently erase saved work.