Are there any plans to get timeline produced full of changes (filters applied to videos imported in playlist) as I describe them in natural language? This might not have any immediate benefit but at later stages some skills.md can be added to them for defining all cool effects we see in videos (ultimately made up of basic filters on fundamental level).
On video editing software level, I see it as extra interface support which takes an AI generated .json or .yaml (consisting file paths of assets and filter names with various values) and produces that .mlt file. Now one can preview that timeline created out of .mlt file and make fine detail edits and export.
1 Like
That is expensive
Our plan is to add a MCP server. Then, you can use the chat/voice/agent tool of your choice.
takes an AI generated
.jsonor.yaml(consisting file paths of assets and filter names with various values) and produces that.mlt
AI can already directly generate MLT XML.
See also https://github.com/HKUDS/CLI-Anything/blob/main/skills/cli-anything-shotcut/SKILL.md
Also, AI can indirectly use the engine MLT to generate XML similar to how Shotcut does it. It has a full API to create and manipulate a multimedia composition and then serialize it: Python (and other scripting languages, if built. package systems often include it including msys2). From the melt MLT CLI you can do -consumer xml to serialize everything constructed via the command line. The above skill is some custom thing to do something similar.
Next, you should see Shotcut’s Shotcut - MLT XML Annotations . The most important one is the first one to let Shotcut open it as a project. But keep in mind that Shotcut cannot represent and edit everything that the engine can handle or construct. For starter, we have not released a UI generator for multitude of filters and links that we do no provide an explicit UI. Likewise, it is possible to use alternative transitions for track blending or to add transition objects between tracks in addition to the track-blending transitions. You can query an AI chat bot that has the Shotcut source code for context to learn about those MLT implementation details, or you can inspect actual Shotcut XML projects.
Headless generated MLT compositions optionally rendered and encoded is not anything new.
A bigger piece to solve is how to get an AI to understand your photo and video library content, recognize faces to match with names, and store “embeddings” in a vector database for semantic search–all in a manner that is efficient and preferably works cross-platform. It is easier to lean on a cloud service that can provide that such as Apple/Google Photos but then you need to upload everything there and pay for it perpetually. I have only read about a local, open source option named immich that has a MCP server. A complication there is the complexity to set it up and give it the power it needs–I mean for non-technical people like the majority of our users. Docker helps but hardware accelerated docker on macOS and Windows is not simple. Good luck trying to get Docker/Windows to use AMD or Intel GPU, Docker/macOS to use Metal, or Docker to use any NPU. 
1 Like
An MCP server will be amazing! I can experiment with Claude Code.
What I really wanted was that - I want to be able to exchange and share “effects”. Currently, for a video to have a particular effect you need to do set of filter selection and value adjustments yourself.
For example, my friend will tell me what filters combinations he used in what way or maybe record a video doing on his set of assets, then share that knowledge with me and then I will redo the steps. What I really wished was there is some common set of knowledge base which consists of all those steps to make that effect. Let’s say, I want to do ghost trail effect. A knowledge base consists of the information and steps like duplicating the video, slowing it down and adjusting the opacity. It takes reference from the knowledge base, takes the video I imported in the playlist (or gave a file path maybe depending upon interface) and then applies that effect (set of edits).
One way currently would be to share entire project with assets to share effects. Or maybe the .mlt file only but then maybe change video paths by hand through a text editor.
I can see currently that knowledge base doesn’t exist either. So, I imagined if the effects could be represented as some .json file then we can exchange that apply on top of my asset through shotcut. Or I can simply hoard a set of effects created by me only in reusable format.
I never meant
I would want it to just understand effects and assets. I don’t want auto edits creator AI which just makes all edits. I want something like filter sets but with higher level of control.
I would love to develop apps/filters/shortcuts on Claude Code then be accessible inside Shotcut. Maybe even a speed ramping tool, radial blur, etc.
Here are quick ideas Claude just came up with:
Scripted batch automation
Claude can write FFmpeg and PowerShell/batch scripts for tasks Shotcut doesn’t natively automate — proxy renaming (you’ve already done this), bulk file conversion, folder watches that pre-process footage before you ever open Shotcut, or auto-applying LUTs to an entire directory of clips.
MLT project file manipulation
Shotcut’s .mlt files are XML, which means Claude can read and modify them directly. You could have Claude parse a project file and: rename all clips in bulk, swap source paths when you move a drive, inject or update LUT references across all video tracks, or extract a cut list. This is especially useful for your footage if you want to do a mass color grade update after the fact.
AI-powered pre-edit scripting
Paste a rough transcript or outline into Claude and get back a shot-by-shot edit script — with approximate timecodes, suggested b-roll notes, and pacing cues — that you then manually execute in Shotcut. Good for travel vlogs where you have a narrative structure in mind before you sit down to edit.
LUT generation pipeline
Claude can help you build a small tool where you describe a mood or look (“golden hour on a beach, slightly faded highlights”) and it generates the LUT math or writes a FFmpeg filtergraph that approximates it — bridging between your Shotcut color work and the LUTs you apply post-export.
Subtitle/caption automation
Claude can take a raw transcript (from Whisper or auto-captions) and reformat it into .srt or .vtt files perfectly timed for Shotcut’s subtitle track — fixing timing drift, merging broken lines, or splitting overly long captions.
Edit decision list (EDL) generation for Shorts/Reels repurposing
Describe which sections of a long video you want to pull for a Short, and Claude can write a script that uses FFmpeg to cut and stitch those segments — fitting your existing single-line command preference — without reopening Shotcut at all.
Project template generator
Claude can generate a ready-to-open .mlt project file pre-configured with your standard track layout (video tracks, audio tracks, color grade track, title track), your preferred proxy settings, and your LUTs already linked — saving you the setup ritual for every new video.