AppsVideo Studio

● Autessa Video Studio · AI video generator

Your script in. A finished short out.

Autessa Video Studio is an AI video generator that turns a script, or a set of photos, into a finished vertical 9:16 video with an image for every scene, AI voiceover, background music and word-timed captions. Your exact words are kept, rendering is free, and it works from your first script. Video Studio is free with every Autessa account, for unlimited users; you pay only for AI tasks. Because it runs in Autessa, you can shape the look, voices and workflow to your company.

1080 × 1920 MP4Social-ready caption stylesAI, recorded or uploaded voice.srt + .ass captions
Maple Street house tour · Video Studio● RenderedSAMPLE

  1. 1 Script

  2. 2 Scenes

  3. 3 Images

  4. 4 Voiceover

  5. 5 Finish

Script · 58 words · ≈ 24s

Meet Maple Street. Three bedrooms, two baths and a yard the dog will love. The kitchen was redone last spring, with room for everyone. Book a tour today.
01
02
03
Meet Maple Street

01 · Meet Maple Street

02 · Three bedrooms

03 · A kitchen that cooks

04 · Book a tour today

In one sentence

What is Autessa Video Studio?

Autessa Video Studio is a script-to-video and text-to-video tool built into every Autessa account. It writes or takes your script, cuts it into scenes, generates an AI image for each scene on one consistent character, voices each scene, adds royalty-free music and captions timed to your exact words, and renders a vertical MP4 you can download or share with a public link.

Not the same as Video Creator

Video Studio generates. Video Creator records.

Video Studio makes a narrated, captioned short from a script or photos, with AI images and AI voice. Autessa Video Creator records your screen and camera, lets you trim and crop, and shares the recording through a clean public viewer. Use Video Studio for explainers, listings and social shorts; use Video Creator for walkthroughs and quick updates on camera.

Included with Autessa

Free for your whole company

Everyone on your team can make videos, with no per-seat fees. Video Studio is free with every Autessa account; you pay only for AI tasks such as AI images and AI voice, and rendering is always free.

  • Unlimited users
  • No per-seat fees
  • Pay only for AI tasks

How it works

How does Video Studio turn a script into a video?

Every video moves through five stages. Each stage saves as you go, so you can stop and pick up later.

  1. 1 Script

  2. 2 Scenes

  3. 3 Images

  4. 4 Voiceover

  5. 5 Finish

Booking meetings should not take ten emails. Share one link. Your client picks a time…
1 Booking meetings should not take ten emails.
2 Share one link.
3 Your client picks a time that works for both of you.
Ten emails?

What makes it different

Built for words that matter and videos that move

The parts of Video Studio that go beyond a typical AI video generator, starting with the ones teams notice first.

Your words, kept

Script to video without the rewrite

Paste approved copy or brainstorm a draft, and the Scene Planner cuts it into scenes without changing a word. Punctuation-only adjustments are listed for review, and re-cutting with guidance like “choppier, 4-6 words per scene” changes rhythm, never wording.
  • Scenes are split from your text, never rewritten
  • Edits to a scene update the script to match
  • Enhance with AI only when you ask for it
How the Scene Planner works →
Scenes · Scene Planner4 scenesSAMPLE
01

Booking meetings should not take ten emails.

Image: a person buried under a pile of envelopes

≈3.1s
02

Share one link.

Image: a hand holding up a single glowing link

≈1.4s
03

Your client picks a time that works for both of you.

Image: two people pointing at the same day on a calendar

≈3.4s
04

The invite lands on both calendars, with a reminder the day before.

Image: two phones each showing a calendar invite

≈4.2s
A few punctuation-only adjustments were flagged: scene 4, em dash → comma.
Optional: guide the cut, e.g. "choppier, 4-6 words per scene"
Re-cut scenes

One look, every scene

AI images that stay on character

Every generated image is grounded on one character reference: a hand-drawn stick figure with a locked doodle style by default, or your own photo so fill-ins match a real set. Keep every take, split long scenes into shots, or swap in your own photos, clips and free stock.
  • Stick-figure default or a custom reference
  • Every take kept; pick the best
  • Your uploads matched to scenes by AI
About the character reference →
Character referenceSAMPLE

Every generated image is grounded on this reference, so the look stays consistent across scenes.

Stick figure

Hand-drawn doodle style · style locked

Custom image

e.g. a house-tour photo, so fill-ins match the set

Voice, scene by scene

Fix one line without re-voicing the video

Video Studio gives every scene its own voice clip. Use an AI voice with previews, record yourself with a teleprompter, or upload one finished track. Regenerate a single scene, restore an earlier version, and add a pause so fast voices can breathe.
  • AI voice, your voice, an uploaded track, or none
  • Version history per scene with free restore
  • Edited narration re-voices automatically
About AI voiceover →
Voiceover · AI voiceVoice: Ruth ▾SAMPLE

Each scene gets its own voice clip: redo any single scene without touching the rest.

01

Booking meetings should not take ten emails.

3.1s ↻
02

Share one link.

1.4s ↻
03

Your client picks a time that works for both of you.

3.4s ↻
04

The invite lands on both calendars, with a reminder the day before.

Generating…

AI voice

Generate narration scene-by-scene in a natural AI voice.

Record it yourself

Read each scene aloud with a teleprompter. Free.

Upload a track

Bring one finished narration track. Free.

No voiceover

Music and captions only. Free.

Captions that spell your words right

Word-timed captions aligned to your script

Video Studio does not guess your words with speech-to-text. It already has them in your script, so it times each one to the voiceover. Names, numbers and product terms appear exactly as written, burned in and delivered as .srt and .ass files.
  • Forced alignment to your known words
  • Caption styles previewed before render
  • Clean and captioned versions from one render
How captions are timed →
Captions · word timingAligned to scriptSAMPLE
Your client picks

Script words → voice timing

Your6.21sclient6.38spicks6.74sa7.02stime7.09sthat7.46sworks7.61s

The words come from your script, not from a transcription guess, so every name is spelled the way you wrote it.

Never sit on one shot

Smart pacing proposes the extra shots

Set a target like a new image every 3 seconds. Video Studio checks each scene against estimated and then actual voice timing, proposes extra shots for long ones and drafts a visual prompt for each. You edit, deselect and generate.
  • Analysis and prompt drafts are free
  • Only the shots you keep use AI tasks
  • Ken Burns zooms and pans on every still
About smart pacing →
Pacing · estimatedNew image every 3.0sSAMPLE

Long scenes can get extra images so the video never sits on one shot too long.

01
3.1s
02
2.2s
03
7.4s +2
04
5.2s +1
Scene 3 · shot 2

close-up of a finger tapping a time slot on a phone

Scene 3 · shot 3

both people smiling at matching calendars

Scene 4 · shot 2

a reminder bell ringing above a calendar

Generate 2 shots

No black box

Every building block is yours to open

The brainstorm partner is a real agent. The Scene Planner, Photo Matcher and image generator are real tools. Every video is a row in a Videos table and every scene a row in a Scenes table, ready for your own columns, views and triggers.
  • Resources panel on every project
  • Image tool shared with your agents
  • AI usage shown as task estimates before you spend
About open building blocks →
ResourcesSAMPLE

Everything the studio runs on is a real, inspectable resource. Open any of them to view, edit or build on top.

Brainstorm agent ↗

Collaborative script brainstorming partner.

AGENT

Scene Planner ↗

The tool that cuts your script into scenes.

TOOL

Photo Matcher ↗

The vision tool that assigns uploaded photos to scenes.

TOOL

Image generation ↗

The company image tool shared by the studio and your agents.

TOOL

Videos ↗

One row per project: add your own columns, views and triggers.

TABLE

Scenes ↗

A dependent table: one editable row per scene.

TABLE

AI script brainstorm

Autessa Video Studio includes an AI script writer: chat on the left, the live script document on the right, with a Small, Medium or Large model to choose from.

Read more →

Scene editor

In Video Studio the scene list and the script stay in sync: insert, reorder, edit or delete a scene and the script updates, with Enhance with AI on every field.

Read more →

Shots and takes

Every Video Studio scene keeps its takes: generate new ones, pick the best, and split long scenes into numbered shots that each have their own takes.

Read more →

Your photos and clips

Video Studio takes your own photos and video clips and can match each one to the scene it fits best with AI in one step.

Read more →

Pauses between scenes

Video Studio adds a pause between scenes, 0 to 3 seconds project-wide with per-scene overrides, so fast AI voices get room to breathe.

Read more →

Record your narration

Video Studio lets you record your own voiceover scene by scene with a teleprompter, retake any line, and times the video to your voice.

Read more →

Voiceover version history

Video Studio keeps earlier voiceover versions for every scene so you can play them back and restore one for free.

Read more →

Finishing room

The Video Studio finishing room previews the cut scene by scene with music and caption controls beside it, so the last fixes happen in one place.

Read more →

AI task estimates

Video Studio shows an AI task estimate before every step that uses AI, and keeps recording, uploads, rendering and restores free.

Read more →

Product tour

Every screen in Video Studio

From the projects list to the public watch page, here is what you will work in.

Video Studio+ New videoSAMPLE
⌕ Search videos…
AllIn progressCompleteLast updated ▾

Maple Street house tour

Complete

Scheduling app explainer

Voiceover

Q3 safety reminder

Images

Welcome, new hires

Complete

Video projects →

Every video as a project with a thumbnail and status. Search, filter by In progress or Complete, and sort.

New videoSAMPLE

Title

Maple Street house tour

How do you want to start?

Brainstorm with AI

Draft a script in a quick chat.

Paste a script

Already have one? Drop it in.

Start from images

Photos + on-screen captions. No script.

CancelCreate video

New video →

Three ways to start: Brainstorm with AI, paste a script, or start from images.

Script · BrainstormSmall ▾SAMPLE

Brainstorm

A 30-second product explainer for our new scheduling app
Here is a draft that lands in about 28 seconds. I kept it to one idea per line so it cuts into scenes cleanly.Updated the script →
A room-by-room house tourTurn my bullet points into a script
Ask the assistant to draft or tweak the script…

Enter to send · Shift+Enter for a new line

Script

71 words · ≈ 28s
Booking meetings should not take ten emails. Share one link. Your client picks a time that works for both of you. The invite lands on both calendars, with a reminder the day before. Less back and forth. More time for the work.

Your words stay exactly as written: scenes are split from them, never rewritten.

Script →

Chat on one side, the live script document on the other, with words and estimated seconds.

Scenes · Scene Planner4 scenesSAMPLE
01

Booking meetings should not take ten emails.

Image: a person buried under a pile of envelopes

≈3.1s
02

Share one link.

Image: a hand holding up a single glowing link

≈1.4s
03

Your client picks a time that works for both of you.

Image: two people pointing at the same day on a calendar

≈3.4s
04

The invite lands on both calendars, with a reminder the day before.

Image: two phones each showing a calendar invite

≈4.2s
A few punctuation-only adjustments were flagged: scene 4, em dash → comma.
Optional: guide the cut, e.g. "choppier, 4-6 words per scene"
Re-cut scenes

Scenes →

The plan: narration, image prompt and length per scene, plus re-cut guidance.

Images≈ 6 AI tasksSAMPLE

Scene 1 · 1 take

Scene 2 · 3 takes

Scene 3 · 1 take

Scene 4 · 1 take

Scene 5 · 1 take

Generating…

Scene 6

Style (added automatically): black marker line art on plain white background, hand drawn doodle style, vertical composition

Images →

A grid of 9:16 frames that fill in as each image finishes, with takes behind every tile.

Upload photos1 AI taskSAMPLE

Add your own photos and videos: a house-tour set, product shots, b-roll clips, anything. Videos must be 200 MB or less.

▶ 0:06
01 Welcome to Maple Street✓
02 The kitchen✓
03 A yard for the dog✓
04 Book a tour·
✦ Match to scenes with AI

Upload and match →

Your photos and clips, matched to scenes by AI in one step.

Voiceover · AI voiceVoice: Ruth ▾SAMPLE

Each scene gets its own voice clip: redo any single scene without touching the rest.

01

Booking meetings should not take ten emails.

3.1s ↻
02

Share one link.

1.4s ↻
03

Your client picks a time that works for both of you.

3.4s ↻
04

The invite lands on both calendars, with a reminder the day before.

Generating…

Voiceover →

One voice clip per scene, each playable the moment it finishes.

Finish · finishing room←/→ to moveSAMPLE
The invite lands

Approximate preview: the render is the source of truth.

Music

Bright Side · UpbeatDucks under voice

Captions

ShoutAa Bb

Scene 4 · take

Take 2 ▾Pan → Pause Auto

01

02

03

04

05

Finishing room →

Preview the cut, step through scenes, set music and captions.

RenderFreeSAMPLE

QUEUED

ALIGNING

RENDERING

PACKAGING

DONE

Final video (with captions)
Clean video (no captions)
Captions (.srt)
Captions (.ass)
Everything (.zip)
1080 × 1920 · MP4 · 0:24Changed since last render: free to re-render

Render and downloads →

A free render with captioned and clean MP4s, .srt, .ass and a .zip.

Share “Maple Street house tour”SAMPLE
PrivateSpecific peopleEveryone at company
DLDana Lee
Can edit ▾
MOMarcus Ortiz
Can view ▾
PSPriya Shah
Can view ▾

Team sharing →

Private, specific people or everyone at your company, with edit or view access.

Public linkSAMPLE

Anyone with the link can watch: no Autessa login needed. Great for clients or social reviewers.

…/v/8fK2q

Download allowedExpires Dec 1
CopyRevoke

…/v/Lm40c

View onlyNo expiry
CopyRevoke
☑ Allow downloadExpires (optional)Create link

Public links →

Links anyone can watch, with download, expiry and revoke.

ResourcesSAMPLE

Everything the studio runs on is a real, inspectable resource. Open any of them to view, edit or build on top.

Brainstorm agent ↗

Collaborative script brainstorming partner.

AGENT

Scene Planner ↗

The tool that cuts your script into scenes.

TOOL

Photo Matcher ↗

The vision tool that assigns uploaded photos to scenes.

TOOL

Image generation ↗

The company image tool shared by the studio and your agents.

TOOL

Videos ↗

One row per project: add your own columns, views and triggers.

TABLE

Scenes ↗

A dependent table: one editable row per scene.

TABLE

Resources →

Every agent, tool and table behind the studio, open to inspect and extend.

For your viewers

The public watch page

Anyone with a public link watches the video on a clean page with captions, and a download button if you allowed it. No Autessa login is needed, links can expire, and you can revoke one at any time.

About public share links →
Book a tour today

Maple Street house tour

0:24

↓ Download videoCC Captions

Made with Autessa Video Studio

Caption styles

Caption looks made for short-form video

Shout, TikTok, TikTok Yellow, Outline, Subtle and Karaoke. The preview matches the render.

Book a tour

Shout

Book a tour

TikTok

Book a tour

TikTok Yellow

Book a tour

Outline

Book a tour

Subtle

Book a tour today

Karaoke

Everything in Video Studio

Every area, every feature

Each area has its own page, and every feature has a deep dive.

See every feature →

Use cases

Who makes videos with Video Studio?

Marketing

Product explainers, launch teasers and social shorts from approved copy.

Real estate

Listing tours from the photos you already have, with captions and music.

HR and recruiting

Welcome videos, benefits reminders and job teasers in a consistent style.

Training

Short how-tos and policy reminders, voiced by AI or by your trainer.

Use cases by role and industry →

Integrations

Built on Autessa, with free stock built in

Free stock photos and video from Unsplash and Pexels. Videos and scenes live in AutessaDB tables you can extend. The brainstorm partner is an Autessa agent and the scene and image steps are Autessa tools. Uploads take MP4, MOV and WebM clips and MP3, M4A and WAV narration; downloads are MP4, .srt, .ass and .zip.

All integrations →

Security and control

Your videos, your rules

A role permission decides who can use Video Studio. Each project is private, shared with specific people or with everyone at your company, with edit or view access. Public links can be view-only, expire and be revoked. Video Studio runs on Autessa's own AI models.

Security, sharing and data →

Compare

Evaluating AI video generators?

See how Video Studio stacks up against the tools teams look at alongside it.

VSSynthesia →VSHeyGen →VSPictory →VSInVideo →VSColossyan →

FAQ

Questions people ask about Video Studio

What is Autessa Video Studio?

Autessa Video Studio is an AI video generator built into Autessa. You give it a script, or a set of photos, and it produces a finished vertical 9:16 short video with an image for every scene, voiceover, background music and word-timed captions, rendered as a 1080x1920 MP4.

Is Autessa Video Studio free?

Yes. Autessa Video Studio is free with every Autessa account, for unlimited users. You pay only for AI tasks, such as AI images and AI voice; rendering and re-rendering are free.

How do I turn a script into a video with AI?

Create a video, paste your script or brainstorm one with the AI assistant, and Video Studio does the rest. The Scene Planner splits the script into scenes, each scene gets an AI image, the voiceover is generated scene by scene, and Finish adds music and captions and renders the MP4.

Does Video Studio change the words in my script?

No. Your exact words are kept: scenes are split from your text, never rewritten. The only changes the Scene Planner may make are punctuation-only adjustments, and it lists every one of them for you to review.

How is Video Studio different from Autessa Video Creator?

Video Studio generates a video; Video Creator records one. Video Studio turns a script or photos into a narrated, captioned short with AI images and AI voice. Autessa Video Creator records your screen and camera, lets you trim and crop, and shares the recording through a clean public viewer.

Can Autessa make a video from my own photos?

Yes. Start from images to build a video from photos with an on-screen caption per scene and no script, or upload photos and clips into a scripted video and let AI match each one to the scene it fits best. Videos up to 200 MB per file are accepted.

How are the captions timed?

Captions are aligned to the actual words of your script against the voiceover, not guessed by transcription. That means names, product terms and numbers are spelled exactly as you wrote them, and each caption appears as the words are spoken.

Can I use my own voice?

Yes. Record each scene yourself with the built-in teleprompter, or upload one finished narration track as MP3, M4A or WAV. Both are free. You can also use an AI voice, or make a video with music and captions only.

What does Video Studio export?

A 1080x1920 vertical MP4. You can download the final video with captions burned in, a clean version without captions, the captions as .srt and .ass files, and a .zip with everything, including the scene images.

Can people outside my company watch my video?

Yes, with a public link. Anyone with the link can watch without an Autessa login. You choose whether downloads are allowed, can set an expiry date, and can revoke the link at any time.

How much AI does a video use?

Video Studio shows an estimate in AI tasks before each step that uses AI, so there are no surprises. Brainstorming, scene planning, image generation, photo matching and AI voice use tasks; recording or uploading your own media, rendering, re-rendering and restoring earlier voice versions are free.

Which AI models does Video Studio use?

Video Studio runs on Autessa's own AI models, whatever bring-your-own-model connections your company has set up.

Does it work out of the box?

Yes. Paste a script and you can have a finished, captioned short the same day. Because Video Studio runs in Autessa, you can also shape it to your company: your own character reference and look, voices, music and caption style, and the agent, scene tools and video tables behind it are all open to tailor.

● ROLL CAMERA

Make a video before your coffee cools.

Paste a script or brainstorm one, and Video Studio does the scenes, images, voice, music and captions. Ready out of the box, yours to shape in Autessa, and rendering is free.

Start free

Script → Scenes → Images → Voiceover → Finish · rendering is free

100% customizable, code and all

Make Autessa Video Studio fully your own.

Use it out of the box, then change anything. Ask Autobot, Autessa’s AI builder, for a new field, screen, report, workflow or agent and it builds it into your copy of the app. Or open the code and edit it yourself. Nothing is locked: the app, its data and its code are yours.

Start free and make it yours