A full-screen, multi-track video editor for precise cuts, layered visuals, captions and sound — right in your browser.
Start with a quick automated workflow or open the full editor when you need more control.
Combine clips into a clean sequence with independent trimming, transitions, music and title text.
Take control of your edit with a timeline-based workspace built for detailed video projects.
Your source video is processed in your browser. Audio is sent in short chunks to ClipForge’s Cloudflare Workers AI for transcription; transcript text and timestamps are then used for AI moment selection. Do not upload private or sensitive footage unless you are comfortable with this processing.
Social share links are not supported as direct media. Use a direct video-file URL that allows browser access (CORS), or upload the file.
Upload once. ClipForge reads the dialogue, finds the strongest moments and prepares editable Shorts automatically. Fine-tuning is optional.
Each result is one continuous moment, not a montage of separate clips. AI aims for your selected duration while keeping the dialogue complete.
Auto captions use Cloudflare Workers AI Whisper. Audio is sent to the ClipForge Worker for transcription; choose the spoken language for better results. Caption timing is currently phrase-level, not verified word-level alignment.
Speech-rich and emotional moments score higher than plain loud music. Very large files are scanned by sampling points across the video, which takes a few minutes. You can stop anytime.
Smart reframe first scans the short for faces and scene cuts, then keeps one steady crop per shot and hard-cuts to whoever is speaking, like an edited drama clip, instead of panning. The preview below stays centered. The scan adds a few seconds before recording.
“Dialogue only” sends each short’s audio to Cloudflare Workers AI for transcription, then cuts detected gaps between spoken lines. Results depend on transcription accuracy and may need review.
Karaoke and Highlight styles animate caption emphasis. Caption timing is currently estimated from phrase timestamps; exact word-level highlighting is not guaranteed. Urdu Nastaliq uses a dedicated Urdu font, while transcription accuracy depends on the audio and selected language.
Step 1: analysis scans the video for its strongest moments. Long episodes take a few minutes; you can stop anytime.
Checks sample frames for static logos, sponsor banners and still title cards, and replaces those shorts with other picks. It cannot recognise a brand product that appears inside a normal scene.
Choose a file from your device. Nothing is uploaded anywhere.
Speech activity, emotional peaks and strong openings are scored second by second.
The top moments become 9:16 clips. Save each one to your device.
Every short gets a score and tags like “Strong hook” or “Dialogue”.
Picks come from the whole video, and “Different picks” re-rolls them.
The 9:16 window follows faces and snaps on scene cuts.
Your video never leaves the device. Only the optional AI models are downloaded.
Clips are recorded in real time from the player, so a 30 second short takes about 30 seconds. Keep the page open and the screen on while exporting.
Older versions ranked by raw loudness, which favors theme music and intros. Now speech activity and peaks relative to the scene around them are used, intro and credits are skipped, and picks are spread across the video. Tap “Different picks” for a new set.
Cloudflare Workers AI Whisper transcribes audio sent in short chunks from your browser. The resulting transcript and timestamps are sent to the AI selection service to identify context, hooks, emotional turns and memorable dialogue. The original video file is not uploaded by the Shorts workflow. AI suggestions still need human review.
Before a short is recorded, a small face detector (downloaded once) scans it for faces and scene cuts. Each shot then gets one steady 9:16 crop that follows the speaker only when they really move, and it jumps exactly on cuts. If the detector cannot load, it falls back to motion.
No. Browsers cannot download YouTube videos, and its terms do not allow it. Download your own video from YouTube Studio and choose the file. Direct .mp4 links work if the site allows it.
Cloudflare Workers AI Whisper transcribes the audio for each selected short. No local speech-model download is required. The app captures each short’s audio in the browser and sends it to the Worker; transcription time depends on clip length, server availability and network speed.
While a short is recorded, ClipForge jumps over quiet stretches, so the result is tighter than the chosen length. Aggressive removes shorter pauses.
Latest Chrome or Edge (v126 or newer) on Android and desktop, or Safari. Shorts are always saved as MP4. Firefox cannot record MP4, so it is not supported.