Edit videos in Claude and ChatGPT

Yes. Connect Makemancer and Claude, ChatGPT or Codex can edit a video you already have: cut and reorder moments, reframe to 9:16, burn in word-timed captions, replace or mix the sound, join clips, make slow motion and clean up a voice. Simple edits such as a trim cost $0.02; captions on a one-minute clip cost $0.06.

Bring
A video or audio file, and what to change
Get
An edited MP4 or audio file
From
2 credits · $0.02

Made with it

Our own results, first takes. Each caption says what it took.

Keep only the moment you want

A 5-second draft cut down to 3 seconds, starting one second in. Trims, joins and reorders work on the file you have; nothing is generated again, so the picture is exactly the original.

InA paper airplane in a classroom, H3 Max Turbo 480p draftMiniMax H3 Max Turbo · 480p · 5 s · 16:9 · 25 credits
ResultA 3-second 480p cut of the paper airplane draft, the upscaling sourceTrim Video · 3 s · 2 credits

Slow motion from a normal clip

A 5-second drone shot at 30 fps, slowed to half speed by Topaz Apollo, which draws the frames in between instead of repeating them. It is charged per generated frame, so trim first and slow down only what you need.

InDrone shot over the sea toward a lighthouse, Wan 3.0Wan 3.0 · 720p · 5 s · 16:9 · 65 credits
ResultThe drone shot in 2× slow motion (Topaz Apollo)Topaz Apollo · 121 credits

New sound on the same picture

A clip of a fictional woman talking and a new spoken line. The line replaced the clip's sound, starting one second in. The picture is untouched, so her mouth no longer matches; lip sync is the next step when it should.

InA fictional woman recording a video message, the source clipMiniMax H3 · 768p · 6 s · 16:9 · 96 credits
InThe new line for the lip sync, Gemini TTSHi everyone, quick update: the new studio opens next Monday, and you are all invited.Gemini 3.8 Flash TTS · 2 credits
ResultThe source clip with the new line laid on its own soundtrackAdd Audio To Video · 2 credits

A voice pulled out of a noisy room

A podcast intro mixed over café noise, then cleaned: ElevenLabs Voice Isolation removed the café and kept only the speaker. It takes audio or video and returns the voice as audio, ready to lay back on the clip.

ResultThe noisy café mix cleaned by Voice IsolatorElevenLabs Voice Isolation · 80 credits

How to do it

  1. Connect Makemancer

    Add Makemancer to Claude, ChatGPT, Claude Code or Codex. The steps for each client are on the connection page.

  2. Bring the footage and say what to keep

    Attach the file or give a direct link; a post from YouTube, TikTok or Instagram is imported first. Give timestamps for exact cuts, or ask the assistant to transcribe the video and suggest the moments.

    Cut 0:12–0:27 and 1:05–1:20 from this video and join them in that order. Reframe to 9:16 with the speaker centred, keep the original audio and add word-by-word captions. Show me the plan and the cost before you render.
  3. Finish the sound and the pace

    Replace or mix the soundtrack, lay a voiceover or music under it, slow a moment down, or join clips with an intro and outro. Watch the result and ask for one fix at a time.

    Put this voiceover over the clip from the 2-second mark, keep the original sound underneath at 20% volume, then slow the last 3 seconds to half speed.

Which model to use

ModelBest forPriced forCredits
Trim Videoedit/trim-videoCut one stretch out of a video. Sound and picture are kept as they are.per request2$0.02
Cut And Reframeedit/cut-and-reframeCut, reorder and reframe several moments into one MP4, with optional captions.per request2$0.02
Add Subtitlesedit/add-subtitlesTranscribe and burn in word-timed captions, in any Google Font.60 s source6$0.06
Add Audio To Videoedit/add-audioReplace a video's sound, or mix a new track over it at a set second and volume.per request2$0.02
Topaz Apolloframe-interpolation/topaz-apolloSlow motion up to 8 times, or a smoother frame rate up to 120 fps.5 s video input30$0.30
ElevenLabs Voice Isolationaudio/elevenlabs-isolationRemove noise, music and reverb so only the voice remains.60 s source80$0.80

Edit, don't regenerate

An edit keeps your footage: a trim is the same frames, a reframe is the same shot cropped, captions are drawn on top. That makes edits cheap and exact. When the scene itself has to change, such as new words in a speaker's mouth, a different person on screen, or a sharper picture, that is a generation: lip sync, character swap or the upscaler.

Long video into short clips

For an interview or a talk, ask for the transcript first. The assistant can then suggest moments that stand on their own, with timestamps and a one-line reason for each. Pick the ones you want and it cuts them to 9:16 with the speaker in frame and captions where the words matter. Check each crop where people move or turn, and keep faces and key words clear of the app's buttons.

Captions people can read

Captions are timed word by word from the transcript and burned into the video. Choose any Google Font, the colour, the highlight for the current word, the position and how many words show at once. Keep them high enough to clear the app's own buttons on Reels, Shorts and TikTok.

Questions

Is there an AI video editor that works inside Claude or ChatGPT?

Yes. With Makemancer connected, Claude, ChatGPT and Codex can trim, cut, reframe, caption, re-sound, join and slow down your videos by request. The edits run on our servers and come back as files with permanent links.

Can AI edit a video I already have?

Yes. Upload the file or give a direct link, or a post link to import. Edits keep your footage as it is; only the parts you ask to change are changed. To change what is in the picture, a generation tool such as lip sync or character swap does that.

How do I trim, reframe and caption a clip in Claude or ChatGPT?

Give timestamps for the moments to keep, say the frame you want (9:16 for Reels and Shorts, 1:1, 16:9) and ask for captions. The assistant shows the plan and cost, then returns one MP4. You can also ask it to transcribe first and suggest the moments.

Can it clean up the audio or add music?

Yes. ElevenLabs Voice Isolation removes background noise, music and reverb from speech. A new voiceover, a music track or a sound effect can replace the original sound or be mixed under it at the volume you choose.

What does editing cost?

Simple edits such as a trim or a new soundtrack cost $0.02 each, and a reframe $0.02 per started 30 seconds of output. Captions are priced by length, $0.06 for a one-minute clip. Slow motion and voice cleanup cost more and are quoted before they run.