Бросьте сырые кадры в папку. Поговорите с ним, как с помощником редактора. Получите .fcpxml прямо в свою временную шкалу — каждое решение о сокращении, переходе, повторном времени и подписи сопровождается письменным обоснованием, которое вы можете проверить, отклонить или повторить, просто сказав это.

**Ни один другой наполовину запеченный ИИ-редактор, который красиво демоирует и разваливается, как только вы указываете на реальные кадры. Три полосы восприятия — Parakeet ONNX speech, Florence-2 visual captions at 1 fps, CLAP audio events scored against an agent-curated vocabulary — interleaved in one merged_timeline.md Агент читает сквозной текст и причины вместо просмотра пикселей. Точные якоря EDL поступают от helpers/find_quote.py против кэшированных транскриптов — никаких грепов, никаких посторонних. Современные открытые модели, составленные так, как никто другой не отправлял, работают на 100% на вашей машине. Каждая граница разреза проверяется по отношению к исходным зажимам перед экспортом - разрезы среднего слова и визуальные разрывы block FCPXML.

Никакого облака. Никакого черного ящика. Никаких водяных знаков. Без подписки. Пересмотр 50 стоит столько же, сколько и пересмотр 1.

** Это не новинка.

Drop raw footage in a folder. Talk to it like an assistant editor. Get an .fcpxml straight into your timeline — every cut, transition, retime, and caption decision comes with a written rationale you can inspect, reject, or iterate on by just saying so.

Not another half-baked AI editor that demos pretty and falls apart the second you point it at real footage. Three perception lanes — Parakeet ONNX speech, Florence-2 visual captions at 1 fps, CLAP audio events scored against an agent-curated vocabulary — interleaved into a single merged_timeline.md the agent reads end-to-end and reasons over instead of watching pixels. Word-precise EDL anchors come from helpers/find_quote.py against the cached transcripts — no greps, no off-by-one. State-of-the-art open models, composed in a way nobody else has shipped, running 100% on your machine. Every cut boundary is verified against the source clips before export — mid-word cuts and visual discontinuities block the FCPXML.

No cloud. No black box. No watermark. No subscription. Iteration on revision 50 costs the same as revision 1.

This isn’t a novelty. It’s the assistant editor you wish you could hire — doing real assembly work, on your machine, in your NLE. If you edit for a living, it saves you hundreds of hours.

---

premiere-agent

Edit videos by conversation — runs 100% locally and exports straight into Premiere Pro (and Resolve, and Final Cut) with J cuts, L cuts, dissolves, and the rest of the cut vocabulary you’d actually use in an NLE.

Drop raw footage in a folder, chat with your agent (Claude Code — local CLI or cloud workspaces, or Codex CLI / IDE / app), get cut.fcpxml + cut.xml back — XML-only delivery, the cut lives in your NLE. Text + on-demand visuals, no frame-dumping — three perception lanes so the LLM can reason about speech, abstract sounds, and visible objects, not just one of them.

What it does

It’s a conversational video editor — you talk to it like an assistant editor (“trim the filler, J/L the dialogue, timelapse the build sequence, ship it”) and you get back an XML cut you import straight into your NLE.

Drop your raw clips in a folder, run claude or codex in that folder, and the agent walks the loop with you: it inventories the sources, asks a few questions about what you’re going for, runs a one-time preprocess that reduces hours of footage to three small text timelines, proposes a strategy, waits for your OK, writes the cut, self-evaluates every boundary against the source clips, and only then drops cut.fcpxml + cut.xml + master.srt next to your sources. Don’t like a cut? Tell it. Want a different pace? Tell it. The preprocess is cached, so iteration is just re-reasoning over the same timelines — no re-watching, no re-transcribing.