How-to guides

Each guide answers one job: what to type, what Recut does, and what it won't do. Recut is an AI creative agent: you attach your files, say what you want, and it plans the steps, picks the models and runs them, with every price shown first.

Finishing jobs such as trimming, joining, resizing, captions and platform exports run on your own device. Jobs that need an AI model, such as dubbing, upscaling or a voiceover, run on Recut credits or your own provider accounts.

• How to add captions to a video automaticallyAttach a video, type "add captions" and Recut times each word to the speech and burns captions in, styled to read on a phone.
• How to resize a video for TikTok, Reels and ShortsAsk Recut to export a video for TikTok, Instagram Reels or YouTube Shorts: a 9:16 frame at 1080×1920, 30 fps and even loudness.
• How to change a video's aspect ratio (16:9, 9:16, 1:1, 4:5)Make a video vertical, square, 4:5 or widescreen with Recut: crop to fill the frame or keep the whole picture with bars. Runs on your device.
• How to normalize a video's audio loudnessRecut measures a video's loudness and sets it to the level TikTok, Reels, YouTube or LinkedIn play at (-14 or -16 LUFS), with a limiter on peaks.
• How to trim the start or end of a videoTell Recut the times to keep, or say "cut before the first words", and it trims the video on your device in seconds, with no upload to an editor.
• How to turn a long video into a Short or ReelPick the moment by time or by what is said, and Recut cuts it out of the long video, makes it vertical and captions it for Shorts, Reels or TikTok.
• How to merge video clips into one videoAttach your clips, say the order, and Recut joins them into one video fitted to one size, even when the clips differ in shape or have no sound.
• How to add music to a videoAdd your own track to a video with Recut, set its volume, start time and fade-out, or have Recut compose music for the video from a description.
• How to add an AI voiceover to a videoPaste a script, pick a voice, and Recut reads it with an AI voice model and lays the voiceover on your video, with music turned down under it.
• How to remove background noise from a videoRecut takes the sound out of the video, isolates the voice from noise with an AI audio model, and puts the clean voice back on the picture.
• How to extract the audio from a video (MP3 or WAV)Ask Recut to save a video's sound as an MP3 or WAV. It runs on your device with ffmpeg, free of model costs, and keeps the original video.
• How to transcribe a video to textAttach a video and ask for a transcript: Recut takes out the sound and runs a speech-to-text model such as ElevenLabs Scribe or Whisper.
• How to speed up or slow down a videoMake a video from a quarter speed to four times faster with Recut, and choose whether the sound keeps its pitch or rises and falls with the speed.
• How to make a slowed and reverb version of a songRecut slows a track down with its pitch dropping, adds a light or heavy reverb tail, or speeds it up for nightcore. Runs on your device.
• How to turn a video into a GIFAsk Recut to convert a clip to a GIF: 480 pixels wide at 12 frames a second by default, or the size and frame rate you say. Runs on your device.
• How to add a logo or watermark to a videoAttach a video and a logo, and Recut places the logo in a corner or the centre at the size and opacity you choose. Runs on your device.
• How to add a title card or end card to a videoRecut makes a title or end card as a short clip, with your logo, a title, a line under it and a web address, and joins it onto your video.
• How to save a frame from a video as an imageAsk Recut for the frame at any second, or the first, middle or last frame, and it saves it as a full-quality PNG or a smaller JPG.
• How to dub a video into another language with AIRecut runs an AI dubbing model, such as ElevenLabs dubbing, that translates a video's speech into another language in the same voice.
• How to lip sync a video to new audio with AIAttach a video and a voice track, and Recut runs an AI lip-sync model, such as Sync Lipsync or LatentSync, so the mouth follows the new audio.
• How to make a photo talk with AIAttach a portrait and a voice track, and Recut runs a talking-avatar model, such as OmniHuman or Kling AI Avatar, to make the photo speak or sing.
• How to turn a photo into a video with AIAttach a photo, describe the motion, and Recut animates it with an image-to-video model such as Kling, Veo or Seedance, priced before you run.
• How to upscale a video with AIRecut runs an AI video upscaler, such as Topaz or SeedVR, to raise a video's resolution and sharpness, or add frames for a higher frame rate.
• How to add AI sound effects to a silent videoRecut runs a video-to-audio model, such as Mirelo, Kling video-to-audio or MMAudio, that watches a silent clip and makes matching sound.
• How to separate vocals from music in a songRecut runs a stem separation model, such as Demucs or SAM Audio, to split a song into vocals and instruments, or remove the vocals for karaoke.
• How to make a product video ad from one photoRecut's Product shot to ad template turns one product photo into three lifestyle shots and a captioned hero video with an end card.
• How to make a short video ad with AI from a promptDescribe the ad in one sentence and Recut plans the scenes, makes each clip, the narration and the music, and assembles one finished video.