Can Descript be vibe coded?
Text-based audio and video editor with transcription and AI tools
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.
Jump to the build brief ↓Checked Jul 2026
What you pay today, before any DIY hosting
high editorial confidence
Buildability by layer
Screens, forms, and focused interactions
The repeatable job the product performs
Availability and legality of required data
Uptime, queues, support, and maintenance
Security, compliance, and user confidence
The achievable core
- Transcribe media, map words to timestamps, allow text deletion to cut audio/video, then render via ffmpeg.
- Build a focused single-user workflow with real persistence, search, and export.
- A responsive interface with real empty, loading, success, and error states.
The parts a prompt cannot buy
- polished nonlinear editor
- overdub/voice tools
- filler-word workflows
- templates
- The last 20 percent is sync, migration fidelity, speed, and edge cases.
- Model quality and inference operations are part of the product.
Why people still pay
They pay to avoid building and babysitting a media editor, not just for transcription.
The last 20 percent is sync, migration fidelity, speed, and edge cases.
Model quality and inference operations are part of the product.
Permissions, presence, and shared workflows are difficult to simplify.
The brief
Context, requirements, acceptance criteria, non-goals, and the full production standard — as Markdown, ready for any coding agent.
Build brief — a focused alternative to Descript
Context
**Descript** — Text-based audio and video editor with transcription and AI tools. It currently costs $24/mo.
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.
This brief describes a focused, single-operator replacement for the part of Descript that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.
What you are building
Transcribe media, map words to timestamps, allow text deletion to cut audio/video, then render via ffmpeg.
Build a focused single-user workflow with real persistence, search, and export.
A responsive interface with real empty, loading, success, and error states.
Requirements
Functional
Ffmpeg.
Speech-to-text/alignment.
Desktop or web editor.
Video rendering pipeline.
Optional hosted storage.
Non-functional
Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
Security: server-side secrets, validated input, and no credentials in the client bundle.
Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
Portability: the operator can export their data and leave without losing it.
Implementation brief
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.
Delivery standard
Inspect the repository first, then write a short implementation plan before writing code.
Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
Add structured logs around every external call and return actionable errors without leaking sensitive details.
Write unit tests for the core logic and one automated test of the main user journey.
Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.
Acceptance criteria
A clean install starts the app using only the README and .env.example.
The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
Tests, type checking, linting, and a production build all pass with no ignored failures.
No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.
Non-goals
Do not build these, and do not claim to have replaced them:
Polished nonlinear editor.
Overdub/voice tools.
Filler-word workflows.
Templates.
The last 20 percent is sync, migration fidelity, speed, and edge cases.
Model quality and inference operations are part of the product.
What you still own after launch
Run migrations, backups, restores, and dependency updates.
Test the critical journey after every model, API, or hosting change.
Monitor failures and fix the edge cases a first prompt will miss.
Risk
**Manageable.** A personal version is realistic if you test the critical journey and keep reliable backups.
Editorial confidence in this assessment: high. No independent one-shot implementation is linked yet.
Prior art
Working open-source software you can read, fork, or borrow from before starting:
[Kdenlive](https://github.com/KDE/kdenlive) — Mature open-source video editor; useful alternative but not text-first SaaS clone
Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/descript
You still own the product
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
Open-source prior art
Before you start
Can Descript be vibe coded?
Partly, if you narrow it. 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.
What can an AI coding agent reproduce from Descript?
Transcribe media, map words to timestamps, allow text deletion to cut audio/video, then render via ffmpeg. Build a focused single-user workflow with real persistence, search, and export. A responsive interface with real empty, loading, success, and error states.
What will a DIY Descript replacement still be missing?
polished nonlinear editor; overdub/voice tools; filler-word workflows; templates; The last 20 percent is sync, migration fidelity, speed, and edge cases.; Model quality and inference operations are part of the product.
What do I still own after building a Descript alternative?
Run migrations, backups, restores, and dependency updates. Test the critical journey after every model, API, or hosting change. Monitor failures and fix the edge cases a first prompt will miss.