There is a difference between AI that enriches a story and AI that tries to tell one.
The first kind does the analytical work that consumes time without requiring judgment — transcribing every word, scoring every emotional peak, tagging every scene, making the raw material navigable. It hands the result to the editor and steps back. The story remains exactly what it should be: a human decision, made in a timeline, by someone who understands what the footage means.
AVScript is the first kind. The editor makes every cut. The AI makes sure the material you’re cutting — and the team around you — serves that work rather than replacing it.
Here’s what that looks like in practice.
Bring Your Cut into AVScript
The workflow runs in both directions.
When you’re ready to share what you’ve been working on — or you just want the rest of the team to see where the edit is — export FCPXML from Final Cut Pro and import it into AVScript. Your sequence opens as a project: timeline structure, clips, cut decisions, all visible to anyone on the team without them needing FCP installed.
No screen sharing. No “can you send me the project file?” No waiting for someone to install the right version. The producer, director, or client opens AVScript in a browser and sees your current cut — with the searchable transcript and Story AI metadata running alongside it.
This is also where the two directions of the workflow meet. You’ve already uploaded your footage and run Story AI. Now the team can see not just the raw material but exactly how you’ve shaped it — and propose revisions to sequences they can see, rather than guessing from a vague brief.
Today: a manual handoff — export from FCP, import into AVScript. Two steps, takes a minute.
With the FCP extension (coming): every save in FCP syncs your cut to AVScript automatically. The team always sees the current version. No export, no import, no file transfers. Project sync in both directions, flawless, in the background while you work.
Your Timeline Stays Yours
AVScript never modifies your FCP project. It doesn’t import itself into your Library, doesn’t rearrange your clips, and doesn’t propose a cut you didn’t ask for.
What it does: it takes the footage that will eventually land in your timeline, runs it through AI analysis — transcription, emotion scoring, visual tagging — and packages all of that intelligence as FCPXML metadata you import on your own terms.
The two worlds only connect when you choose to import a MetaFlow FCPXML. Until then, your FCP Library is exactly as you left it.
Keep Your Originals. Upload Proxies.
Your camera originals are large. Uploading them to a cloud platform to run AI analysis makes no sense if you already have them on a fast local drive.
There’s a better path: generate proxies in FCP, upload the proxies to AVScript, run all the AI analysis on those, then export MetaFlow FCPXML and relink to your originals in FCP.
same duration
Why this works
FCP’s relink is based on file duration and frame rate, not file name. As long as the proxy and the original have the same duration and frame rate — which they always do when you generate them with FCP’s built-in transcoding — the metadata transfers cleanly. Your RAW files never had to leave your drive.Your Team Works Outside Your Edit
Here’s the part that matters most if you work on documentary, news, or any project with multiple stakeholders who have opinions about the cut.
They will always have opinions. The question is: where do they voice them?
In a traditional workflow, that answer is often “in your Slack DMs” or “over your shoulder with a timecode they read off a screenshot.” You translate their notes into edits. It’s fine. It works. It’s also slow.
AVScript gives them a better lane — without giving them access to your timeline.
A producer can open AVScript, look at the analysed footage, build a sequence from the suggested clips, and send it to you as a project. You open it in AVScript, see what they had in mind, export FCPXML if anything is worth keeping — and the rest never touches your Library.
Nobody is in your edit without your permission. But they’re not sending you WhatsApp voice notes either.
The Storyteller’s Workspace
On most productions there’s a person whose job is to shape the story before it reaches the editor. A producer, a director, a journalist, a story editor — call them the storyteller. Their job is to figure out what gets told, in what order, from which takes. Your job is to make that vision real inside FCP.
The traditional version of this handoff is a timecode log on paper, a shared Google Doc, or a stream of voice notes. Useful, imprecise, and entirely dependent on your ability to translate someone else’s intent into an edit.
AVScript gives the storyteller a dedicated workspace for exactly this — and it works in two completely different situations.
In both cases the workspace is built around the dialogue track — interviews, narration, presenter pieces, anything where words carry the structure. B-roll is on the roadmap; for now the storyteller lays out the verbal spine, and you, the editor, dress it with visuals once it lands in FCP.
When the structure is ready, the storyteller exports two things. First, a PDF script in proper industry format — and we’re genuinely proud of this one. It opens with a full asset list of every media file in the project bin (so anyone reading the script knows exactly which files it references), followed by the script itself: speaker names in caps, frame-accurate timecodes, verbatim dialogue. It looks like a document from a real production, because it is.
Second, the same sequence as FCPXML — so you can open it directly in FCP as a starting point rather than rebuilding it from scratch.
You use the PDF the way your predecessors used a paper cut off a Betacam session: as a roadmap. Read it, note what you’ll reshape, and start cutting. Or import the FCPXML, use what works, and throw out what doesn’t. Either way, you’re starting from something precise rather than from a feeling.
The pitch: get your storyteller on AVScript
If your storyteller is working from a Google Doc or a stack of handwritten notes, you’re doing their translation work for free every time you sit down to cut. Get them on AVScript and that translation disappears. They find the moments themselves. They build the structure themselves. They bring you a PDF and an FCPXML instead of a feeling. Your job becomes editing — not interpreting.When the Client Wants to Choose: Multicam, Text Editing, and Search
Sometimes the storyteller isn’t a producer or a journalist — it’s the client themselves. And sometimes clients don’t just want to approve; they want to participate. Normally that means a screen share, a stream of feedback in the wrong format, or a call where they try to describe timecodes verbally.
AVScript has a better answer for that too.
All of this happens in AVScript, in a browser, without a single login to Final Cut Pro. The client participates productively. You receive structured output — a sequence, a marked-up transcript, a timecode list — instead of a feeling.
What Lands in Your FCP Library
When you import a MetaFlow FCPXML, your source clips gain a layer of intelligence they didn’t have before.
Every source clip has:
- Captions — the full transcript as
<caption>elements, frame-accurate. Jump to any spoken word directly from the FCP timeline. - Keyword collections —
Emotion-Joy,Emotion-Tension,Topic-Interview,Scene-Exterior,Speaker-A— generated from the AI analysis, attached as FCP Keywords. - Markers — any markers you placed in the AVScript timeline carry across.
Once they’re in FCP, Smart Collections do the heavy work. Build a Smart Collection for Emotion-Tension and instantly see every high-tension moment across your entire source library. Filter by Speaker-A to find every line from one interview subject. Search for a word in the timeline search bar and every caption match highlights — across all clips, across all events.
We won’t charge you twice for the same footage. When Story AI processes a file, the data — transcript, emotion scores, visual tags — is stored against the media file permanently, not the project. Use that file in a new project six months from now and MetaFlow exports immediately, at no extra cost. One analysis job. The result is yours for as long as you keep the file.
The Practical Workflow, End to End
Here’s how a real project runs with AVScript alongside FCP:
What AVScript Is (and Isn’t)
The easiest way to understand AVScript is to think about three tools you already know.
Finder manages your files. QuickTime lets you play and inspect them. iMovie lets you arrange them into a rough sequence.
AVScript lives somewhere in between all three — but with a layer none of them have: AI that reads your footage and turns everything it finds into searchable, exportable metadata. You manage your media library. You preview clips. You can build rough sequences. But you’re never in a full NLE. The cut — the real cut — stays in Final Cut Pro, where it belongs.
It is a metadata engine that sits upstream of your NLE — logging every spoken word, scoring every emotional peak, tagging every scene — so that by the time you sit down to cut, you already know where everything is. It doesn’t propose a structure. It doesn’t decide what matters. It makes the material fully transparent so that you can.
The story has an essence. A moment where it lands. AI’s job is to clear the path to that moment. Your job is to recognise it and build toward it. That’s the only division of labour that makes sense — and it’s the one AVScript is built around.
Coming soon: We’re working on a native Final Cut Pro extension. The goal is to bring AVScript’s search, transcripts, and AI metadata directly into your FCP interface — no export/import step, no window switching. When it’s ready, MetaFlow becomes a live connection rather than a handoff.
One more thing worth knowing: AVScript isn’t FCP-only on the output side either. If a project moves to a different NLE mid-production — or a co-production hands footage to a Premiere editor — the storyteller’s work travels there just the same. Premiere Pro gets its own dedicated native XMEML export (File → Import, no Translation Report, no XML bridge): captions land on V2, descriptions appear in the Premiere project bin. DaVinci Resolve accepts FCPXML directly. You’re working in FCP, but nobody else in the chain is locked to it.
The cut is yours. Always has been.
→ Try AVScript with your next project · → MetaFlow FCPXML in detail · → How Story AI works