BuiltbyGSV Lab · AI case study · In Progress
Reelcut
Reelcut is being built for creators, colleges and small teams who record more video than they have time to edit. A creator uploads a long recording and the editor suggests cuts: removing silences and filler, generating word-timed captions, and reframing horizontal footage into vertical formats. Every suggestion stays editable on a timeline before export.
The problem
Short-form video has become the default way to reach an audience, but turning a 40-minute talk or a raw recording into a few strong reels still takes hours of trimming, captioning and reframing by hand.
The product response
Reelcut pairs speech transcription with a timeline editor. The transcript becomes the editing surface: deleting words removes the matching footage, silences can be cut in one step, captions are timed to each word, and vertical crops follow the speaker. AI proposes edits; the creator approves them.
Most editing time goes into finding the good parts. Reelcut starts from the transcript, so a creator can scan what was said, keep the strongest moments and let the timeline follow.
AI handles the repetitive passes: silences, filler words, captions and reframing. The creator keeps the final say on every cut before anything is exported.
Scope and technology
Reelcut is an AI-assisted video editor in development at BuiltbyGSV Lab. It turns long recordings into short, captioned reels by combining speech transcription with a timeline editor: creators can edit through the transcript, remove silences, generate word-timed captions and reframe footage for vertical formats. AI suggestions remain editable before export.
- Status: In Progress
- Engagement: BuiltbyGSV Lab
- Technology: React, TypeScript, FFmpeg, Whisper, WebCodecs
- Year: 2026
Next steps
Open a private beta for creators Add brand caption templates Support multi-speaker reframing Add direct export to social platforms