AI text to video maker

From words to a visual direction.

Paste a script or describe an idea, and Shotmatic narrates it over AI-generated scenes with captions, in the voice and style you pick.

Turn your text into a video Run it from the API

Text to video in Shotmatic means the words you give it become the narration, and the pictures are made to fit them. Paste a finished script and it is read as written. Describe an idea instead, and Shotmatic drafts the script first, so you can edit it before any scene exists.

This is the same Faceless Short format as the faceless video generator, approached from the writing side. It suits people who already have the words: a newsletter paragraph, a lesson, a product update or a story, ready to become a narrated video without filming.

Examples made in Shotmatic

Real outputs from Shotmatic's own account, with the settings behind each one and the credits it was charged.

Why your coffee tastes bitter

A 30-second vertical tip in the Sketch Black&White style: grind sizes, a kettle, a French press with a four-minute timer, narrated by Sloane with Bold captions.

Format: Faceless Short
Visual style: Sketch Black&White
Image quality: Standard
Voice: Sloane
Captions: Bold
Length: 31 seconds
Aspect ratio: 9:16
Music: On
Credits quoted: 100

Script

Is your coffee bitter? Often it isn't the beans' fault. It's over-extraction: the water pulled too much out of the grounds. Here are three fixes. First, grind a little coarser, because finer grounds extract faster, bitter compounds included. Second, let boiling water rest for thirty seconds before you pour. Third, shorten the brew: four minutes is plenty for a French press. Change one thing at a time and taste the difference. Your next cup can be smoother with the beans you already have.

Made by Shotmatic on its internal QA account from a script Shotmatic wrote; the images and narration were generated in the render. Sloane is one of the creator's catalog voices and the music is the built-in track "dont stop me abstract future bass".

Make one like this

How to repot a houseplant

A 45-second widescreen how-to: photographic Cinematic scenes of a root-bound pot, watering, easing the plant out and adding fresh mix, narrated by Darian with Story captions.

Format: Faceless Short
Visual style: Cinematic
Image quality: Standard
Voice: Darian
Captions: Story
Length: 45 seconds
Aspect ratio: 16:9
Music: On
Credits quoted: 140

Script

Your houseplant needs a bigger pot when its roots circle the bottom or push out of the drainage holes. Here's how to move it with less stress. Water the plant a day before, so the root ball slides out in one piece. Pick a pot one size up, about two inches wider, with a drainage hole. Tip the plant on its side, hold it at the base of the stems, and ease it out. If the roots are wound in a tight circle, gently loosen the outer ones with your fingers so they grow out into the new mix. Add fresh potting mix to the new pot, set the plant at the same depth it grew before, and fill in around it. Water slowly until it runs out of the drainage hole. Then give it a week out of harsh sun while it settles in. Most houseplants only need this every year or two.

Made by Shotmatic on its internal QA account from a script Shotmatic wrote; the images and narration were generated in the render. Darian is one of the creator's catalog voices and the music is the built-in track "constellations".

Make one like this

How your text becomes scenes

Shotmatic splits the script into scenes, and the number of scenes follows the length you choose: four for about 30 seconds, six for 45 and eight for anything longer. Each scene gets a generated image, or AI video motion if you pick a motion option, and the price follows the same scene count.

The narration uses one of 12 voices, and you can play a sample of each before you choose. Captions follow the spoken words, in one of 4 caption styles.

Writing text that narrates well

A narrator reads about two to three words a second, so a 30-second video holds roughly 60 to 80 words. Lead with the point, keep one idea per sentence, and write numbers the way they should be read aloud.

Read the script out loud once before you generate. If a sentence makes you pause for breath, split it; if a line only makes sense with a picture you cannot describe in words, rewrite it so the narration carries the meaning on its own.

How it works

01
Idea or script
A finished script, or an idea for Shotmatic to draft a script from.
02
Script and settings
Edit the script, then pick the voice, visual style, caption style and length.
03
Credit quote
The creator shows the price before you approve; nothing is generated until you do.
04
Narrated short
Shotmatic generates the scenes and narration and adds captions. Download the MP4 and post it on your channels yourself.

What you control

Aspect ratio4 options: Vertical 9:16 · Social portrait 4:5 · Square 1:1 · Horizontal 16:9
Length: 15 to 180 seconds on a paid planUp to 30 seconds without one.
Visual style6 options: Cinematic
Animated
Sketch Black&White
Classic Animation
Hand-painted Anime
Anime
Images or motion5 options: AI images in every scene · AI video for the first scene, then images · AI video for the opening scenes, then images · AI video and images in alternating scenes · AI video in every sceneAI video motion costs more credits than images.
Caption style4 options: Viral · Bold · Minimal · Story
Narrator voice12 options: Adam - Deep & Firm · Russell - British Narrator · Sawyer - Movie Trailer Voice · Kael - Energetic Presenter · Tyler - Young & Upbeat · Kira - Bright & Friendly · Elise - Soft & Gentle · Sloane - Polished Professional · Bella - Warm Storyteller · Darian - Grounded Narrator · Adam - Dark & Brooding · Nora - Warm & ClearPlay a sample of each in the creator.
Script language8 options: English · Spanish · French · German · Italian · Dutch · Portuguese · Portuguese (Brazil)
Music: 18 built-in tracks, or no music

Limits and availability

A pasted script is narrated as written, so typos, names and numbers are read exactly as you typed them.
Shotmatic doesn't post anything for you. Download the finished MP4 and upload it to your channel or ad account yourself.
Without a paid plan, videos are capped at 30 seconds. Paid plans can target 15 to 180 seconds.
Generated scenes illustrate the script; they are not footage of real events. Check anything factual before you publish.

What it costs

The two examples above were quoted at 100 and 140 credits before they rendered. That quote is what the render charges; Shotmatic's own account is not billed.

With AI images, a video costs 100 credits at about 30 seconds (four scenes), 140 at 45 seconds and 180 for anything longer. Ultra images and AI video motion cost more, and each script draft costs 20 credits.

See plan prices and monthly credits

Questions

Is my script read word for word?

Yes, when you paste it. If you ask Shotmatic to draft a script from an idea, you can edit the draft before you create the video.

How is this different from the faceless video generator?

Both use the Faceless Short format. This page starts from your text; the faceless page starts from a topic or a channel idea.

How many scenes will my video have?

It follows the length: four scenes for about 30 seconds, six for 45 and eight for anything longer.

Can I choose the voice?

Yes, from 12 narrator voices, and you can play a sample of each in the creator before you generate.

Can I make a horizontal or square video?

Yes. Choose 9:16, 4:5, 1:1 or 16:9 before you generate.

Run it from code or an agent

The hosted MCP server and the REST API run the same creation steps. This is the plan_video call for this format; angle brackets mark your own values.

{
  "tool": "plan_video",
  "arguments": {
    "goal": "Narrate my script as a 45-second vertical video for TikTok",
    "script": "<your script>",
    "duration_seconds": 45,
    "voice_id": "<voice id from shotmatic://voices>"
  }
}

Recommends a Faceless Short with the brief_video archetype; the create_session payload carries your text as source.kind "script".

Read the API and MCP guide