Skip to content

AI TikTok video maker

Make TikTok videos with AI that speak your audience's dialect

Write a hook and a few lines. Vocla voices them in Saudi, Emirati, Kuwaiti, Egyptian, Jordanian, Lebanese, Maghrebi (Darija) or Modern Standard Arabic, generates vertical scenes timed to the voice and burns in Arabic captions, so the video works with the sound on or off.

  • Vertical 9:16 on every video plan
  • Arabic captions that render correctly
  • Approve the storyboard before you render

Video is included from the Starter plan. The Free plan doesn't include video.

Keyboard: space plays or pauses, M turns sound on or off, F is full screen, left and right arrows skip 5 seconds.
Made with Vocla Video · Emirati voice
0:00 / 0:14
Full-frame vertical video, ready to upload
9:16
Scenes timed to the voice-over, one idea each
3–8 s
Voice, Arabic captions and optional music in one file
MP4

How it works

From idea to posted in 4 steps

No camera, no microphone, no editing timeline. You keep control at every step, and nothing renders until you approve it.

  1. 1

    Step 1

    Write the hook, then the script

    Start with a first line you can say in about two seconds, then one short sentence per idea. Check the timing with the script planner on this page.

  2. 2

    Step 2

    Pick the voice, dialect and 9:16

    Choose a Vocla voice and the dialect your viewers speak, the vertical format, a caption style (clean, bold or karaoke) and an optional music bed.

  3. 3

    Step 3

    Approve the scenes

    Vocla voices the script, splits it into short scenes timed to the speech and writes a visual prompt for each. Edit any prompt and approve a storyboard of stills before rendering.

  4. 4

    Step 4

    Render, download and post

    Get an MP4 with your voice, burned-in Arabic captions and music, then upload it to TikTok like any video you filmed. If one scene misses, regenerate only that scene.

Free tool · runs in your browser

TikTok script planner

Paste a script to estimate how long it takes to say, see how it splits into scenes, check your hook and get a credit estimate before you open Vocla.

Arabic, English or French. One short sentence per idea works best.

Pace
Target length

Your plan

Estimate

Spoken duration
13.4 s31 words
Scenes
33–8 s
Lite tier
2,400Every video plan

Suggested scene timeline

0 sTarget length: 15 s15.0 s
  1. Scene 10.0–5.2 sHookPerfume fading fast? Spray it on your pulse points, not your clothes.
  2. Scene 25.2–10.4 sPut on a little unscented moisturiser first. Don't rub your wrists together.
  3. Scene 310.4–13.4 sSave this video and try it tomorrow.
  • Hook checkYour hook takes about 1.2 s to say: short enough to land before people scroll.
  • Length checkAbout right for a 15 s video.
  • Plan that fitsFits Starter: videos up to 15 s, 30 s of video a month.

Estimated Vocla credits

Lite tierEvery video plan
2,400 credits
Standard tierProfessional and up
6,000 credits
Storyboard stills (optional)
600 credits

Scenes are rounded up to the clip lengths each tier renders. Add the voice-over (priced by the speech model) and the music bed if you use one. The quote in the app before rendering is exact.

Estimates from average speaking rates. The real voice-over sets the exact timing, and Vocla times the scenes to it.

Make this video in Vocla

Video is included from the Starter plan. Your script never leaves this browser.

What works on TikTok

Six habits of short videos people finish

Practical rules we built the planner around. None of them needs a big budget, only a tighter script.

  • 0–2 s

    Hook in the first two seconds

    Open on the question, the number or the result. Don't spend the first second on a greeting or a logo: viewers decide to stay or swipe almost immediately.

  • 15–60 s

    One idea, the right length

    Fifteen seconds fits one tip or one offer, and Starter's per-video limit. Thirty to sixty seconds fits a how-to, a tour or a short story on Professional.

  • 9:16

    Vertical and full frame

    Render in 9:16 so nothing is letterboxed, and keep the subject in the middle of the frame where the eye lands first.

  • CC

    Captions on, always

    Plenty of people scroll with the sound off. Burned-in Arabic captions in bold or karaoke style keep the message readable on mute.

  • 3–5 s

    A new shot every few seconds

    Change the picture with every sentence. Vocla scenes last three to eight seconds, which gives short videos a lively, trend-style rhythm.

  • CTA

    End with one clear ask

    Follow, save, comment or visit: pick one. A single call to action at the end is easier to act on than three.

Mind the edges

TikTok draws its own buttons, account name and caption text over the right side and the bottom of the video. Keep your subject away from the edges and place captions in the center if your scenes allow it.

Real renderOne script, seven dialects

Hear one script in every market

The same short video in seven Arabic dialects. Switch while it plays.

Saudi, Emirati, Kuwaiti, Egyptian, Levantine, Moroccan and Modern Standard Arabic.

Keyboard: space plays or pauses, M turns sound on or off, F is full screen, left and right arrows skip 5 seconds.
Made with Vocla Video · Saudi voice
0:00 / 0:12

Ideas

Not sure what to post?

Six formats that suit an AI voice-over and generated scenes. The blog has fifty more, grouped by niche.

  • Food and cafésOne dish, three ways: a quick recipe voiced in Egyptian, one scene per step.
  • Real estateA sixty-second tour that describes a property room by room in a warm Gulf voice.
  • E-commerceTurn a product photo into the first frame of a fifteen-second ad (from Starter).
  • EducationOne idea a day in Modern Standard Arabic, with captions for viewers on mute.
  • TravelThree hidden spots in one city, each with its own scene and a single sentence.
  • FitnessA fifteen-second stretch for people who sit all day, counted out by the voice.

Plans and limits

Video limits on every plan

Starter covers short vertical clips; Professional adds longer videos, 1080p, every format and no watermark.

Everything in each plan, side by side
FeatureFreeBasicStarterCreatorProfessionalBusinessEnterprise
Vocla Video: video per monthNot includedNot included30 seconds1 minute5 minutes15 minutes30 minutes
Vocla Video: longest videoNot includedNot included15 seconds20 seconds1 minute2 minutes3 minutes
Vocla Video: maximum resolutionNot includedNot included720p720p1080p1080p4K
Vocla Video: formatsNot includedNot included9:169:16 · 16:9 · 1:19:16 · 16:9 · 1:19:16 · 16:9 · 1:19:16 · 16:9 · 1:1
Vocla Video: quality tiersNot includedNot includedLiteLite · StandardLite · StandardLite · Standard · ProLite · Standard · Pro
Vocla Video: product photo as first frameNot includedNot includedIncludedIncludedIncludedIncludedIncluded
Vocla Video without watermarkNot includedNot includedNot includedIncludedIncludedIncludedIncluded

Video is included from the Starter plan. The Free plan doesn't include video.

Compare all plans

Questions about making TikTok videos with AI

What is an AI TikTok video maker?

A tool that turns a written script into a finished vertical video without filming. In Vocla, the script is voiced in the dialect you choose, split into short scenes timed to the speech, generated with AI and delivered as an MP4 with Arabic captions and optional music.

Can I make TikTok videos in Arabic with AI?

Yes. Every word is spoken by a Vocla voice in Saudi, Emirati, Kuwaiti, Egyptian, Jordanian, Lebanese, Maghrebi (Darija) or Modern Standard Arabic, and the captions are a separate track rendered with proper Arabic shaping, right to left. English and French voices are available too.

How long can my TikTok video be?

Up to 15 seconds per video on Starter (30 seconds of video a month), up to 60 seconds on Professional (300 seconds a month), up to 120 seconds on Business (900 seconds a month) and up to 180 seconds on Enterprise.

Do I need to film anything?

No. Each scene is generated from a visual prompt that Vocla writes and you can edit. From Starter up you can also upload a product photo to use as the first frame.

Will the Arabic captions look right?

Yes. The video model never draws text, because models tend to garble Arabic letters. Captions are burned in from a separate track timed to the voice, in clean, bold or karaoke style, at the bottom or center of the frame.

Is there a watermark?

Starter videos carry a small watermark. Professional, Business and Enterprise videos render without one, which is what you want for ads and client work.

How do I post the video to TikTok?

Download the MP4 and upload it to TikTok the same way you would upload a video you filmed, from your phone or computer. Vocla doesn't post to your account for you.

Is the script planner free, and is it accurate?

It's free and runs entirely in your browser: nothing you type is sent anywhere. Its timings come from average speaking rates, so treat them as an estimate; the real voice-over and the in-app quote are exact.

Start in minutes

Give your content a voice today

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

  • ⁠500͏⁠ free credits every month
  • No card required
  • Arabic and English interface