New in 2.4 SceneSync, four ways to sync

Your audio. Your images and clips. Synced into a video.

Bring your own voiceover or song and your own photos and video clips. SceneSync lines them up: picture changes in the speaker's pauses, at the exact times you set, from a scene sheet, or on the beat of the music.

Start free trial See the four modes
  • Images and video clips, mixed
  • Never cuts mid-word
  • Your recording plays in one piece
  • 9:16 and 16:9
  • 4ways to sync
  • 0.1 sExact Match timing
  • 0cuts in the middle of a word
  • JPG · PNGimages, plus MP4 clips
  • 2sizes, 9:16 and 16:9
Four modes

Pick how your images and clips follow the audio

Each mode is for a different starting point. All four end on the same timeline, ready to polish and export.

Mode 1

Auto Split

Slideshows and quick videos

Number your images and clips in order and SceneSync spreads them across the audio. It cuts where the speaker pauses, so the picture never changes in the middle of a word.

  • A Pacing slider, from a strict even split to following the speaker's pauses
  • Name files 01.jpg, 02.mp4, 03.png and they line up by themselves, images and clips together: 2 comes before 10
  • Told about a number used twice, a missing number or a file with no number
  • Drag a picture to its place, type a new position, or nudge it with the arrows
  • Warned when a picture would only flash on screen, or there are too many for the audio
Mode 2

Exact Match

When you already know your timings

Say exactly when each image or clip starts, and it starts there to the tenth of a second. Put the time in the file name, or bring a timing file instead of renaming anything.

  • In the file name: 02_00-07.5.jpg starts at 0:07.5, 14_1-02-03.mp4 at 1:02:03
  • A cue sheet (.txt or .csv): one picture per line, with a time and its file name, number or a chapter title
  • Audacity labels: press Ctrl+B at each picture change while the audio plays, then export them
  • Subtitles (.srt or .vtt): picture 1 starts with subtitle 1, picture 2 with subtitle 2
  • Images and clips without a time are spread between the timed ones around them
  • Snap to pauses moves each time up to 0.3 s into the nearest pause, if you want it
Mode 3

Transcribe & Guide

Starting from a recording

Have the audio but no pictures yet? SceneSync transcribes it and splits it into scenes on its sentences, then tells you exactly what pictures to make.

  • Let SceneSync choose how many scenes, or ask for an exact number
  • See the average, shortest and longest scene; join or split any of them
  • Save a scene sheet as a text file and a spreadsheet, with an empty images folder ready to fill
  • The sheet tells you what size to make the pictures for 16:9 or 9:16
  • Name each picture with its scene number, and each scene is shown next to its picture
  • Not finished? Create now and add the pictures later from the SceneSync home
Mode 4

Beat Sync

Music videos and montages

Bring a song and your images and clips, and every cut lands on the beat. SceneSync finds the tempo, every beat and the start of every bar by itself, with no API key.

  • Cut every beat, every 2 beats, every bar, every 2 bars or every 4 bars
  • Follow the energy: faster cuts where the music is loud, slower where it is quiet
  • Spread your images and clips over the whole song, or loop a handful to fill it
  • Fix a tempo read at double or half speed with ×2 or ÷2, or tap along
  • Each cut lands with a quick zoom punch, and a flash marks the drop or the chorus
  • Follows a band that speeds up or slows down, and tells you when there is no steady beat
Exact Match

Already timed it? Bring the times with you.

Times in a timing file win over times in file names, and a timing file in your pictures folder is picked up by itself. A table shows every picture's start, how long it is on screen and where its time came from.

You're told about two pictures at the same time, a time past the end of the audio, a cue line that names no picture, and pictures listed out of order, which one button puts right.

How it works

Made to be checked before you create it

Every mode ends with the Timing step: your pictures, your audio and every cut, before anything is made.

Your recording, in one piece

Your original audio plays from start to finish in the export, with no clicks or gaps at the cuts.

Captions that follow your voice

SceneSync transcribes your audio as soon as you choose it, with your Groq or OpenAI key, and the captions follow it word by word.

Images and video clips, mixed

Use JPG or PNG images and MP4 video clips in the same video. Choose a whole folder or pick files.

Clips play as they are

Images can get a slow zoom; a video clip plays as it was shot, with no zoom added. A clip shorter than its slot loops, so it never freezes on screen.

Any common audio file

Your voiceover or song can be MP3, WAV, M4A, AAC, OGG or FLAC, and it stays the soundtrack of the whole video.

Check it before you create it

Play the timing with your pictures, and drag any cut on the waveform to move it.

Shorts or YouTube

Pick 16:9 or 9:16, a slow zoom on pictures and fades between them.

Then the full timeline

Your video opens on the timeline: caption style, music, the opening hook, colour looks, sound effects, layers, preview and export.

FAQ

Questions about SceneSync

How the modes work, what you need and what it costs.

Still have a question? Send us a message and we'll help you out. Contact us
What is SceneSync?

A way to make a video from audio, images and video clips you already have. Choose your voiceover or song, add your images and clips, and SceneSync decides when each one comes on screen. It has its own place in the sidebar, separate from AI videos, and your video then opens on the normal timeline.

Which SceneSync mode should I use?

Auto Split if your pictures are in order and you want them spread across a voiceover. Exact Match if you already know when each picture should start. Transcribe & Guide if you have the audio but no pictures yet. Beat Sync for music.

Can I use video clips, not just images?

Yes. Use JPG or PNG for images and MP4 for video clips, mixed in the same folder and numbered in the same sequence. Images get a slow zoom if you turn it on; clips play as they were shot. A clip shorter than its slot loops, and your audio stays the soundtrack throughout.

Which file types should I use?

JPG or PNG for images, MP4 for video clips, and MP3, WAV, M4A, AAC, OGG or FLAC for your audio. If a clip is in another format, such as MOV or MKV, save it as MP4 first.

How do I put my images and clips in order?

Name them with a number: 01.jpg, 02.jpg, 03.mp4 and so on. 2 comes before 10, and files without a number go to the end. You can also drag a picture to its place, type a new position or nudge it with the arrows, and an order you set by hand is kept when you add more.

Do I need an API key?

For captions, and for Transcribe & Guide, you need a Groq key (free) or an OpenAI key to transcribe the audio. Without a key, Auto Split and Exact Match still make the video, just without captions; with subtitles as your timing file, their text becomes the captions. Beat Sync needs no key at all.

Can I set the exact time each picture starts?

Yes, with Exact Match. Put the time in the file name, like 02_00-07.5.jpg for 0:07.5 (use - instead of :, because Windows does not allow colons in file names), or bring a cue sheet, Audacity labels or an .srt or .vtt subtitle file. A timing file in your pictures folder is found and used by itself.

Will a picture change in the middle of a word?

Not in Auto Split, which only changes picture in the speaker's pauses, or in Transcribe & Guide, which splits on sentences. In Exact Match your times are used as given, and Snap to pauses can move each one up to 0.3 seconds into the nearest pause.

Can I add an opening hook, music or a colour look?

Yes. A SceneSync video opens on the same timeline as every other project, so caption styles, music, the opening hook, colour looks, sound effects, layers and export all work as usual.

Does a SceneSync video count toward my videos?

It counts as one video, the same as an AI video, when you first export it. Exporting it again is free. During the free trial that is one of your 3 videos a day; paid plans have no limit.

Get started

Turn the audio and pictures you already have into a video.

Free for 7 days. No card needed. Works on Windows and macOS.

Start free trial See pricing