Skip to content
English
Start free
Open menu

AI video editNew

Edit any clip with a sentence. Remove, add, replace.

Upload a short video, say what should change, and get it back edited in a few minutes: an object gone, a product added, a character swapped. The picture changes. Your sound does not.

Edit a clip nowSee how it works
  • Original audio never regenerated
  • Clips from 3 to 15 seconds
  • Write the instruction in Arabic or English

Included in the Professional, Business and Enterprise plans.

BeforeAfter
Keyboard: space plays or pauses, M turns sound on or off, F is full screen, left and right arrows skip 5 seconds.
Edited with Vocla
0:00 / 0:09
Before: Original clip

The sound you hear is the edited clip's: the original audio, untouched.

Drag the divider to compare the original clip with the edit.

Clip length per edit
3–15 s
Reference photos for Add and Replace
1–4
Output, by quality tier
720p · 1080p
Changes to your original sound
0

Three edits

One clip, three things you can do to it

Pick the edit, write one instruction, and add reference photos when the edit needs them.

How it works

From your clip to the edit in three steps

No timeline, no masks, no keyframes. You bring the clip and say what you want.

  1. Keyboard: space plays or pauses, M turns sound on or off, F is full screen, left and right arrows skip 5 seconds.
    Edited with Vocla
    0:00 / 0:09
    1

    Upload your clip

    A video of 3 to 15 seconds in MP4, MOV or WebM, with or without sound. Vertical clips for TikTok and Reels work best.

  2. The reference photo used for the edit
    Reference photo
    Your instructionReplace the woman in the clip with the person in the photo
    2

    Say what changes

    Choose Remove, Add or Replace and write one instruction. For Add and Replace, upload a reference photo of what or who should appear, up to four.

  3. Keyboard: space plays or pauses, M turns sound on or off, F is full screen, left and right arrows skip 5 seconds.
    Edited with Vocla
    0:00 / 0:09
    3

    Get the edited video

    A few minutes later the edit is ready in 720p or 1080p, with your original audio laid back exactly as it was. Download it or edit the original again.

Sound stays yours

The picture is edited. The audio is never touched.

Most AI video tools invent a new soundtrack with the new picture. Vocla does the opposite: only the frames are repainted, then your original audio is laid back under them, sample for sample.

  • No regenerated voicesYour voice, your music and your room sound are the same file you uploaded, not an imitation of it.
  • Lips stay in stepThe edit keeps the clip's timing frame for frame, so speech still lines up with the mouths on screen.
  • Trend sounds surviveThe beat, the punchline and the pause land exactly where they did in your take.
BeforeOriginal audio
AfterEdited picture
Same audio, untouched

Who it is for

Built for clips that have to go out today

The edits people used to open a compositing suite for, done from a sentence.

Where the edits go

Made for the feeds you post to

Ideas, examples and posting notes for each one.

Limits and specs

What the editor takes and what it returns

The facts to know before you upload.

SettingWhat applies
Clip length3 to 15 seconds per edit
FormatsMP4, MOV or WebM, with or without sound
EditsRemove, Add or Replace: one per run
Reference photosNone for Remove; 1 to 4 for Add and Replace
InstructionOne sentence or a few, in Arabic or English
Output720p or 1080p, depending on the quality tier
AudioThe original sound, laid back unchanged
TimeA few minutes per edit

Each plan has a monthly allowance of edit seconds. The studio shows what is left before you start.

Plans and credits

Included in Professional, Business and Enterprise

AI video edit is part of the plan, paid with the same credits as the rest of Vocla. An edit is charged per second of the clip, by quality tier, and the studio shows the cost before you confirm.

Compare plansEdit a clip now
Plans that include it
  • Professional
  • Business
  • Enterprise
  • Charged per second of the clip, in credits
  • A failed or refused edit is refunded in full
  • A monthly allowance of edit seconds on every included plan

Safety and consent

Edit responsibly

Changing who or what appears in a video is powerful. These rules apply to every edit.

  • Your clip, your rights

    Upload only clips you filmed or have the right to edit and publish.

  • Consent of everyone shown

    You need the permission of every person in the clip and in the reference photos, and you confirm it before each edit.

  • What is not accepted

    No public figures, no minors and no nudity. Edits that break the policy are refused and refunded.

  • Marked as AI-edited

    Edited clips carry an AI-edited marker, and platforms ask you to label realistic AI edits when you post.

Read the acceptable use policy

AI video edit: questions people ask

How do I remove an object from a video with AI?

Upload a clip of 3 to 15 seconds, choose Remove and describe what should go and where it is, for example "the white cup on the table, bottom right". Vocla erases it from every frame and rebuilds the background behind it. No reference photo is needed.

How do I remove a person from a video?

The same way: choose Remove and describe the person by position and appearance, such as "the man in the blue shirt walking behind me". It works best when the person covers a small part of the frame. You need the right to edit the clip.

How do I add an object to a video with AI?

Choose Add, upload a clear reference photo of the object and say where it belongs, for example "place the bottle from the photo on the table next to her hand". The object is placed in the scene with matching light and follows the camera.

How do I replace a person in a video with AI?

Choose Replace, upload one clear photo of the new person and say who they replace. The new character follows the original movement, timing and framing, and the original audio stays as it was. You need the consent of everyone shown.

Can I replace two people in one video?

Yes. One edit can replace up to four characters, with one reference photo for each. Name them in order in your instruction, for example "the man on the left becomes the person in photo 1 and the woman on the right becomes the person in photo 2".

Does AI video edit change the audio?

No. The AI only repaints the picture. Your original audio is laid back under the edited frames unchanged, with no re-voicing and no regenerated music, and the clip keeps its timing so speech still lines up.

What clips can I upload, and how long does an edit take?

Clips of 3 to 15 seconds in MP4, MOV or WebM, with or without sound. The result comes back in 720p or 1080p, depending on the quality tier, usually within a few minutes. The finished video is saved to your Library.

Can I write the instruction in Arabic?

Yes. Write what you want in Arabic or English, in plain words. Say what the thing looks like and where it is in the frame: the clearer the description, the cleaner the edit.

Which plans include AI video edit, and what does it cost?

It is included in the Professional, Business and Enterprise plans. Each edit is charged in credits per second of the clip, by quality tier, and you see the cost before you confirm. An edit that fails or is refused is refunded in full.

Am I allowed to edit a video with other people in it?

Only with their permission. You must have the rights to the clip and the consent of every person in it and in the reference photos. Public figures, minors and nudity are not accepted, and edited clips carry an AI-edited marker.

More you can do with AI video edit

Start in minutes

Give your content a voice today

Start free with ⁠500͏⁠ credits every month. No card required.

Create your free accountSee pricing
  • ⁠500͏⁠ free credits every month
  • No card required
  • Arabic and English interface