ChatCut is a professional-grade AI video editor anyone can use, even without editing experience. Say how you want your video edited using ChatCut’s built-in agent, or connect your ChatGPT/Codex or Claude Code.
AI understands your footage, intent, and timeline, then helps you make structural edits, fine-tune cuts, and add captions, B-roll, music, voiceover, motion graphics, stock footage, and AI-generated video - all in one place. Every change remains editable on a real timeline.
Video editor built for humans & AI. Edit with GPT & Claude.
Introducing ChatCut Desktop, the AI video editor built for humans and agents to edit together. Use ChatCut’s built-in agent, or connect ChatGPT/Codex or Claude Code. Say how you want your video edited and watch them happen on a fully editable timeline. Edit footage, create motion graphics and captions, generate video, images, music and SFX, and save reusable editing skills. Everything runs locally, and you stay in control. Export XML to Premiere Pro, DaVinci Resolve or CapCut.
Putting XML export behind the subscription is the pricing decision I'd watch. Local editing and letting people bring their own Claude Code tokens are the generous parts, but export to Premiere and Resolve is the escape hatch, and charging for the escape hatch is what makes people feel locked in even when the rest is free. Gating Seedance and Kling generation makes sense because that's real marginal cost. The handoff isn't.
@asadmalik901 Thank you for the thoughtful feedback! Will forward this to the team.
Report
@alimastrickland If it's useful to pass on, the specific ask is one line on the pricing page saying whether XML export stays behind the subscription. Anyone weighing this today is comparing it against a free Resolve round trip, and that line is what settles it.
Turning a 20-minute interview into a 2-minute reel with just a prompt is a great use case. How well does it pick the right moments in longer, messier raw footage?
Report
Congrats on the desktop launch. You let people run it on the ChatGPT or Claude Code tokens they already pay for, which makes core editing free. That is a lot to give away.
Report
using the tokens I already pay for is a smart model, but curious how it works for a heavy edit - like "cut every silence and add captions" on a 40 minute file. does the agent send the whole timeline/transcript context to Claude Code or Codex for that, or is the actual cutting/rendering done locally and the LLM just issues a small set of instructions? asking because that's the difference between it being basically free and it quietly eating a chunk of my daily token budget on one video.
Veltrix AI
Looks really useful. Congrats on the launch!
ChatCut
@oleksandr_drohomyretskyi2 Thank you!
Interesting product here
Putting XML export behind the subscription is the pricing decision I'd watch. Local editing and letting people bring their own Claude Code tokens are the generous parts, but export to Premiere and Resolve is the escape hatch, and charging for the escape hatch is what makes people feel locked in even when the rest is free. Gating Seedance and Kling generation makes sense because that's real marginal cost. The handoff isn't.
ChatCut
@asadmalik901 Thank you for the thoughtful feedback! Will forward this to the team.
@alimastrickland If it's useful to pass on, the specific ask is one line on the pricing page saying whether XML export stays behind the subscription. Anyone weighing this today is comparing it against a free Resolve round trip, and that line is what settles it.
ChatCut
@asadmalik901 Will do.
Softorino 💻📲
Turning a 20-minute interview into a 2-minute reel with just a prompt is a great use case. How well does it pick the right moments in longer, messier raw footage?
Congrats on the desktop launch. You let people run it on the ChatGPT or Claude Code tokens they already pay for, which makes core editing free. That is a lot to give away.
using the tokens I already pay for is a smart model, but curious how it works for a heavy edit - like "cut every silence and add captions" on a 40 minute file. does the agent send the whole timeline/transcript context to Claude Code or Codex for that, or is the actual cutting/rendering done locally and the LLM just issues a small set of instructions? asking because that's the difference between it being basically free and it quietly eating a chunk of my daily token budget on one video.
EverTutor AI
Congrats on the launch! Love the idea of connecting AI agents directly to the editing workflow. Curious to see how far this can go
ChatCut
@suryansh_tiwari2 Thank you!