---
title: When to use Descript vs invideo
description: Descript to edit a recording by its transcript, with your team in real time. invideo when your agent and you share one live timeline with branches.
---
It depends on how you want to edit. Use Descript when you edit a recording by deleting words in its transcript, and want filler words gone in one click. Use invideo when you want every cut on a timeline, and your agent to run the whole job in the project you have open.

Descript lets several people work in one project in real time, with live cursors, and keeps a version history you can restore; its agent works through Underlord and does not see the edits you make in the app. invideo is a multiplayer editor: you, your teammates and your agents work in one cloud project at the same time and watch every edit land live, each agent under its own name. Every timeline has branches, checkpoints and tags, like git branches for code: each person or agent works on their own branch, you compare the branches, restore any checkpoint, and make the winning branch the default. Anyone you share with can fork the project.

The job: a one hour podcast episode, cut into a clean full episode with captions.

**In Descript.** Descript transcribes the episode. You "Edit your words to edit your video": you delete lines in the text and the video follows. You cut filler words "in a click", then add captions. Your co-host edits in the same project at the same time. An agent reaches Descript through its MCP server or API, which hand the work to Underlord. Descript's own blog says the agent does not see the edits you make in the app.

**In invideo.** Your agent transcribes the episode with `media` `audio.transcript` and reads it with the speakers and times. It finds the ums with the transcript and the long pauses with `audio.content`. It cuts them on a branch with `split_clip` and `delete_clip`, adds captions with `add_captions`, and checks frames with `capture`. You watch each cut land in the browser. Every cut is a timeline edit, so you or the agent can undo one later.

## At a glance

Checked on 29 October 2026 against Descript's site, and on 3 November 2026 for collaboration and agent access. They may change.

| | Descript | invideo |
| --- | --- | --- |
| Editable timeline after the cut | Yes, the edit follows the text | Yes, every cut on a branch |
| Collaboration | Several people in one project in real time, with live cursors | People and named agents in one cloud project, with branches and checkpoints |
| Versions | Version history with restore; no branches | Branches, checkpoints and tags on every timeline |
| Generation | AI video, images, voices and voice clones | Video, image, voice and music models |
| Captions | Captions in one click | `add_captions` from the transcript |
| Agent access | Underlord, its own AI editor, plus an API and an MCP server | CLI and skills for terminal agents; MCP server for clients without a shell |
| Project files out | XML for Premiere Pro and DaVinci Resolve, FCPXML for Final Cut Pro | A project for Premiere Pro, Final Cut Pro or DaVinci Resolve |
| Offline | Not stated on its site | No, invideo runs in the cloud |
| Batch | Not stated on its site | `duplicate_timeline` and `export` per clip, run in parts |

## Use Descript when

Descript is built for editing by text.

- You want to edit by deleting words in a document.
- You want one button for filler words and retakes.
- Your team edits one recording together, live.
- You also export for Reaper, Audition or Pro Tools.

## What Descript does better

Say it plainly. Descript is better at some things.

- **Editing by text.** Its whole editor is the transcript. invideo shows a timeline; the transcript is something your agent reads.
- **One-click filler words.** It does it in one click. In invideo, your agent finds the ums and cuts them as separate edits.
- **Live co-editing for people.** Several people edit one project at once, with live cursors.
- **More export targets.** It also exports for Reaper, Audition and Pro Tools.

## Use invideo when

invideo fits the job when the transcript is only the start.

- You want the cuts as real timeline edits you can move or undo.
- You want your agent to see your edits, and you to see its edits, in the same live project.
- Your agent runs the pipeline end to end: transcript, cuts, captions, music, export.
- You build your own pipeline in Claude Code or Codex, and you want the edit steps as named tools, not a separate app.
- You want to try two cuts on branches and keep the one you like as the default.

## Use both

Keep Descript for the text edit, and use invideo for the finish. Export the cut as MP4 from Descript. Your agent adds it with `add_media`, then adds brand captions, music and the other platform sizes.

## Related

- [AI video tools compared, including invideo](/compare/alternatives)
- [When to use OpusClip vs invideo](/compare/opusclip)
- [When to use ChatCut vs invideo](/compare/chatcut)
- [Edit a podcast episode and pull clips from it](/how-to/creators/podcast-edit-and-clips)
- [Cut ums, pauses and retakes, as reversible timeline edits](/how-to/creators/cut-ums-and-retakes)