[verdict][generated prompt][source: descript.com]
Can I vibecode Descript?
// buildable in a weekend, but real gaps stay open
You can build transcript-based cutting for simple clips, but Descript's editor, media pipeline, AI voice/video tooling, publishing, and collaboration are a serious product.
confidence: high
what it is: Text-based audio and video editor with transcription and AI tools
Buildability index · an editorial game
- Price 24 $/month weight: plus 2
- Time multi-day weight: plus 1
- Category audio and video no weight
- Moat execution quality · proprietary models · collaboration weight: minus 4
- Confidence high weight: plus 1
- What you lose 6 items weight: minus 3
- Site descript.com (si apre in una nuova scheda) no weight
The moat outweighs the price: rebuilding this is a project, not an evening.
Gioco editoriale: il verdetto dice se un agente può, l’indice se conviene.
What you build
Transcribe media, map words to timestamps, allow text deletion to cut audio/video, then render via ffmpeg.
what you need
- ffmpeg
- speech-to-text/alignment
- desktop or web editor
- video rendering pipeline
- optional hosted storage
Great boundary case where a toy clone is easy but the product depth is obvious.
The prompt
A weekend with a coding agent. The gaps that stay are right below, under “what you lose”.
Build me a text-based clip cutter to replace Descript for simple edits. Requirements:
- A local web app: Node + Express with a plain JS frontend, binds to localhost.
- I drop an audio/video file into ./media/; the app transcribes it with whisperX
for word-level timestamps, or the OpenAI Whisper API if a key is in .env.
- The transcript renders as clickable words. I select and delete words or whole
sentences; deleted spans go into a cut list I can undo from.
- Render: build one ffmpeg trim/concat command that removes the cut spans from
the original and writes ./output/<name>-cut.mp4 (or .mp3 for audio-only).
- Pad each cut by about 80 ms so words are not clipped mid-syllable.
- Save each project as JSON next to the media file (transcript + cut list) so an
edit can be reopened later.
- No accounts, no telemetry; everything stays on my machine except the optional
Whisper API call.
- Out of scope: multitrack timeline, overdub or AI voices, filler-word
auto-removal, cloud anything. This is a cutter, not an editor.
- README: installing ffmpeg and whisperX, and a warning that local
transcription of long video is slow on CPU.Prompt generated from the data on this page, not reviewed by hand yet. In English on purpose — it is the language coding agents work best in.
What you lose
- polished nonlinear editor
- overdub/voice tools
- filler-word workflows
- templates
- cloud collaboration
- rendering reliability
Why people still pay
They pay to avoid building and babysitting a media editor, not just for transcription.
moat: Execution quality Proprietary models Collaboration what a moat is
media pipeline/collaboration
Free alternatives
Not in the mood to build it? These already exist, they are free or open source, and we checked them one by one.
Rejected (1) — and why
- whisper.cpp (si apre in una nuova scheda) — Excellent transcription engine; entirely missing the finished audio-and-video editor around it.
Who has already built it
Starting from here is still vibecoding: the prompt is for when you want it exactly your way.
- Kdenlive (opens in a new tab) — Mature open-source video editor; useful alternative but not text-first SaaS clone. (alive)
Do you agree?
The vote balance
Ancora nessun voto: il tuo è il primo.
Nessun voto ancora — il primo pesa.
