I've had Claude Code drive DaVinci Resolve before in three ways:
- Generate .otio files that are imported. Unfortunately, .otio doesn't fully support everything Resolve can do.
- Resolve has a scripting engine. Claude can write Lua scripts, then execute the script (through UI Automation)
- Computer Use. It's quite token intense, but it works.
I didn't try it, but for the paid version, someone also built a MCP server based on the scripting engine.
I'm programmatically adding analysis to sim racing lap guides, therefore my flow is probably different from the usual editing flow, but I have to say I found Claude Code + Opus to be quite capable of making edits with computer use.
I had AI write a program to edit with resolve. It does transcription, looks at the transcript and decides where to make cuts. If does a decent job and saves me a bunch of time.
> DaVinci Resolve 21.1 now supports integration with AI assistants such as Claude, Claude Code and ChatGPT Codex, allowing customers to analyze projects, organize media, adjust settings and batch render using everyday conversational language. Customers can ask their AI assistant to create highlight edits from long form video, remove unwanted clips and render deliverables, so they can spend more time being creative rather than getting bogged down in repetitive tasks.
I have videographer friends, and this is exactly what they've been asking for. Their dream is to be able to say "sync the A and B camera footage, chunk the whole interview down into segments, and then pull together the highlights based on this outline."
Not every application of AI is "do the creativity for me."
If we can get the environmental impact of this stuff ameliorated (a big if), this is the real benefit of this kind of AI assistance imo- it transforms everyone into a director and frees them from being a surrogate for a director.
See also: 3D modeling. Autodesk Fusion's interface is truly awful and people put years into learning it to do complex things. The MCP server functionality they added, though still in its infancy with Claude and what it can do, vastly lowers the barrier to entry for people just looking to get into making basic things. They can focus on making the actual creative process rather than fumbling with the awkward tooling.
I'm not complaining either, I wouldn't call myself a video editor, but I do end up spending some of my time in Resolve, and anything to remove the dreadful monotonous tasks of editing interviews is welcome. Although Resolve already makes it pretty easy, with the "edit by moving the transcript around" feature which is amazing. Anyway, I'm happy about being able to sick Codex at Resolve now :)
These 'integrations' everywhere just mean we get more APIs that can be accessed programmatically, which I think is good for users, even if you don't plan to use to use AI. It's like the optimistic web 2.0 APIs everywhere days
Seems like an unusually boring Resolve release. There's nothing there I particularly want to try out. Nothing wrong with that, I've just got used to every release having a ton of shiny new stuff in it.
I guess the agentic stuff is probably exciting to somebody.
I've had Claude Code drive DaVinci Resolve before in three ways: - Generate .otio files that are imported. Unfortunately, .otio doesn't fully support everything Resolve can do. - Resolve has a scripting engine. Claude can write Lua scripts, then execute the script (through UI Automation) - Computer Use. It's quite token intense, but it works.
I didn't try it, but for the paid version, someone also built a MCP server based on the scripting engine.
I'm programmatically adding analysis to sim racing lap guides, therefore my flow is probably different from the usual editing flow, but I have to say I found Claude Code + Opus to be quite capable of making edits with computer use.
I had AI write a program to edit with resolve. It does transcription, looks at the transcript and decides where to make cuts. If does a decent job and saves me a bunch of time.
Not even BMD is safe from the agent apocalypse:
> DaVinci Resolve 21.1 now supports integration with AI assistants such as Claude, Claude Code and ChatGPT Codex, allowing customers to analyze projects, organize media, adjust settings and batch render using everyday conversational language. Customers can ask their AI assistant to create highlight edits from long form video, remove unwanted clips and render deliverables, so they can spend more time being creative rather than getting bogged down in repetitive tasks.
I have videographer friends, and this is exactly what they've been asking for. Their dream is to be able to say "sync the A and B camera footage, chunk the whole interview down into segments, and then pull together the highlights based on this outline."
Not every application of AI is "do the creativity for me."
[delayed]
If we can get the environmental impact of this stuff ameliorated (a big if), this is the real benefit of this kind of AI assistance imo- it transforms everyone into a director and frees them from being a surrogate for a director.
See also: 3D modeling. Autodesk Fusion's interface is truly awful and people put years into learning it to do complex things. The MCP server functionality they added, though still in its infancy with Claude and what it can do, vastly lowers the barrier to entry for people just looking to get into making basic things. They can focus on making the actual creative process rather than fumbling with the awkward tooling.
Pretty soon there will be no need for recording and editing .
IIRC House MD was one of the first shows to use digital (5D mkII).
Soon there will be AI generated shows. Perhaps entirely personalized.
Youtube, generate me a TNG episode.
And full of product placements...
I'm not complaining either, I wouldn't call myself a video editor, but I do end up spending some of my time in Resolve, and anything to remove the dreadful monotonous tasks of editing interviews is welcome. Although Resolve already makes it pretty easy, with the "edit by moving the transcript around" feature which is amazing. Anyway, I'm happy about being able to sick Codex at Resolve now :)
>Not every application of AI is "do the creativity for me."
However it can lead to AI "doing the creative for them" and them out of a job in the near future.
Sure, in the future everything will have a healthy piss-tint yellow shine. =3
Resolve has had de-aging filters, and TTS voice synthesis for awhile.
If the chat-bot/spy-ware aren't integrated, than I don't see a problem with LLM plug-in opt-in support. =3
These 'integrations' everywhere just mean we get more APIs that can be accessed programmatically, which I think is good for users, even if you don't plan to use to use AI. It's like the optimistic web 2.0 APIs everywhere days
They've added it as people are opting for stuff like Palmier Pro, FableCut, and likes, which can edit videos using AI.
I can imagine the conversation with Studio lawyers about contaminating IP with uncopyrightable generative content liabilities. =3
Furthermore, can one use custom API endpoint or is it forced use of corpo AI?
Seems like an unusually boring Resolve release. There's nothing there I particularly want to try out. Nothing wrong with that, I've just got used to every release having a ton of shiny new stuff in it.
I guess the agentic stuff is probably exciting to somebody.