LTX-2.5 AI Video Generator: Text to Video & Image to Video

Generate AI videos with sound from a text prompt or a picture with LTX-2.5. Describe a scene and get a 5- or 10-second MP4 with audio in 16:9, 9:16 or 1:1, at up to 1344 × 768. Or give it a photo and it brings the photo to life (image to video). It is a text to video API you can call from the Console, Python, JavaScript, Make, Zapier or n8n. You need no GPU, no AI provider account and no subscription. It costs $0.096 per 5-second video and $0.116 per 10-second video, and videos stopped before generation starts cost nothing.

deAPI AI tools

• Need higher quality and reference images? → MiniMax H3 AI Video Generator: Text to Video, Image to Video
• Photos too small? → AI Image Upscaler 4x: Upscale Images to 4K & 8K in Bulk
• Need a cutout for the first frame? → AI Background Remover API: Remove BG to Transparent PNG

What does LTX-2.5 AI Video Generator do?

It is an AI video generator built on the open LTX-2.5 video model. For each video you ask for, the Actor:

1. Reads your prompt, and downloads and checks your start image if you gave one.
2. Has LTX-2.5 generate the video, picture and sound together, at 24 frames per second.
3. Saves the MP4 to your Apify storage. It comes back as a download link with its resolution, length, seed and what was billed.

There are two modes:

• Text to video. You describe the scene and the model invents it.
• Image to video. Your picture becomes the first frame and the prompt says how it moves. You can also give an end frame, and the video moves from one picture to the other.

Why use it?

• Video with sound. Ambience, effects and music are generated with the picture, so the clip needs no extra work.
• Cheap. $0.096 per 5-second HD video, well under Wan 2.2 ($0.175) and about a third of MiniMax ($0.30) on Apify.
• Every format for social. 16:9 for YouTube, 9:16 for TikTok, Reels and Shorts, and 1:1 for feeds.
• Batch up to 10 videos per run. Ten prompts, or ten product photos, give ten videos in one run.
• Reproducible. Every video reports its seed; the same prompt, settings and seed give the same video again.
• Pay per video, no subscription. You pay when a video starts generating; inputs refused before that cost nothing.

What data can you get?

Data	Details
🎬 Video	A download link (videoUrl) to the MP4 in your run's key-value store.
📐 Format	aspectRatio, width, height, durationSeconds, fps.
🔊 Sound	hasAudio: whether the file has a sound track.
🎲 Seed	The seed used, so you can reproduce the video.
🧭 Mode	text-to-video or image-to-video, plus the image links you gave.
💵 Billing	billedEvent: the charge for this video.

How to generate a video with AI

1. Open the Actor and write a prompt: the subject, what happens, the setting, the camera and the light.
2. Optionally paste a start image URL to animate a picture.
3. Pick the duration (5 or 10 s) and the aspect ratio.
4. Click Start. A 5-second video usually takes about one minute.
5. Open the Output tab and download the MP4.

Writing a good prompt

• Describe one shot, not a story: "a red fox trotting through fresh snow in a pine forest at sunrise".
• Name the camera: "slow push in", "tracking shot", "aerial drone shot", "handheld close-up".
• Name the light and the mood: "soft golden light", "neon reflections on wet asphalt".
• Name the sound if it matters: "snow crunching underfoot", "rain on the window", "crowd cheering".
• For image to video, describe the movement, not the picture: "steam rising from the mug, slow push in".

Sizes and lengths

Aspect ratio	Resolution	For
16:9	1344 × 768	YouTube, websites, presentations
9:16	768 × 1344	TikTok, Instagram Reels, YouTube Shorts
1:1	960 × 960	Instagram and Facebook feeds

Videos are 5 or 10 seconds at 24 fps, with sound, in H.264 MP4. Auto takes the shape of your start image, or 16:9 for text to video.

How fast is it?

A 5-second video usually takes about one minute: 57–75 s in our tests. A 10-second video takes longer. A run keeps two videos in progress at a time, so a batch of 10 takes roughly 6–15 minutes. When many people generate at once, a video can wait in a queue first.

Input

Field	Type	Description
prompt	string	What the video shows. Up to 2,500 characters.
imageUrl	string	Optional start image (image to video): JPG, PNG or WebP, at least 64 px a side, up to 25 MB.
lastFrameUrl	string	Optional end image, with a start image only.
duration	"5" / "10"	Length in seconds. Default "5".
aspectRatio	auto / 16:9 / 9:16 / 1:1	Default auto.
seed	integer	Optional, for a reproducible video.
videos	array	Optional batch: up to 10 objects with prompt and optionally imageUrl, lastFrameUrl, duration, aspectRatio and seed.

{
    "videos": [
        {"prompt": "A paper boat drifting down a rainy city street, close-up, rain sounds"},
        {"prompt": "Steam rising from the coffee mug, slow push in", "imageUrl": "https://example.com/mug.jpg"},
        {"prompt": "Waves rolling onto a beach at dusk, aerial shot", "duration": "10", "aspectRatio": "9:16"}
    ]
}

Output

One row per video, in the order of the input:

{
    "prompt": "Steam rising from the coffee mug, slow cinematic push in, soft morning light, quiet cafe ambience",
    "mode": "image-to-video",
    "imageUrl": "https://upload.wikimedia.org/wikipedia/commons/thumb/1/1f/Coffee_Mug_%28Unsplash%29.jpg/1280px-Coffee_Mug_%28Unsplash%29.jpg",
    "status": "success",
    "videoUrl": "https://api.apify.com/v2/key-value-stores/.../records/01-steam-rising-from-the-coffee-mug-slow-cinematic-pu.mp4",
    "kvsKey": "01-steam-rising-from-the-coffee-mug-slow-cinematic-pu.mp4",
    "model": "LTX-2.5",
    "quality": "hd",
    "aspectRatio": "16:9",
    "width": 1344,
    "height": 768,
    "durationSeconds": 5.04,
    "fps": 24,
    "hasAudio": true,
    "seed": 11,
    "fileMB": 0.84,
    "generationSeconds": 57,
    "billedEvent": "video-5s",
    "error": null
}

A video that could not be made has "status": "failed" and an error that says why. One that was left out, for example by the per-run limit, has "status": "skipped" and is not charged. A video whose generation had already started is charged even if it then fails; its error says so.

How much does it cost?

You pay per video delivered. There is no subscription and no minimum.

Video	Price
5 seconds, any aspect ratio	$0.096
10 seconds, any aspect ratio	$0.116

• Text to video and image to video cost the same.
• 100 five-second videos cost $9.60.
• You pay when a video starts generating. Anything stopped before that is free: an image that can't be used, a prompt refused on submit, a free-plan or per-run limit, or your budget. Once generation has started the video is charged, even if you abort the run.
• Free plan: 1 five-second video per day (resets at 00:00 UTC) and 10 per calendar month, within a daily capacity shared by all free users. Free-plan videos are paid from your monthly Apify credit like any other run. Paid Apify plans lift these limits.
• Every plan: at most 10 videos per run.

Use cases

• Social media content: vertical 9:16 clips for TikTok, Reels and Shorts from a single sentence.
• Product videos: animate a product photo into a short clip for an online shop or an ad.
• B-roll and stock footage: landscapes, cities, weather and textures for edits.
• Storyboards and concepts: try a scene before you shoot it.
• Automated pipelines: write prompts with an LLM, then generate videos in bulk through the API.

Tutorial: generate videos with the API

1. One video in the Console

Write a prompt, click Start, and download the MP4 from the Output tab.

2. Bring a photo to life

Paste a start image URL and describe the movement: "the camera slowly pushes in, steam rises". Leave the aspect ratio on Auto to keep the picture's shape.

3. From Python

from apify_client import ApifyClient

client = ApifyClient("<YOUR_APIFY_TOKEN>")
run = client.actor("deapi/ltx-video-generator").call(run_input={
    "prompt": "A red fox trotting through fresh snow at sunrise, tracking shot",
    "duration": "5",
    "aspectRatio": "16:9",
})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item["status"], item.get("videoUrl"), item.get("error"))

4. From JavaScript or cURL

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: '<YOUR_APIFY_TOKEN>' });
const run = await client.actor('deapi/ltx-video-generator').call({
    prompt: 'Neon-lit Tokyo street at night in the rain, slow dolly shot',
    aspectRatio: '9:16',
});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items[0].videoUrl);

curl -X POST "https://api.apify.com/v2/acts/deapi~ltx-video-generator/run-sync-get-dataset-items?token=<YOUR_APIFY_TOKEN>" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Waves rolling onto a beach at dusk, aerial shot", "duration": "10"}'

Text to video API and integrations

Run it from Make, Zapier, n8n or a webhook, or chain it after another Actor: write prompts with an LLM, or animate the images another Actor collected. The MP4 links in the dataset can be downloaded by any tool. The Apify API and the Python and JavaScript clients work with it as they do with any Actor.

FAQ

How do I make an AI video from text?

Write a prompt describing the scene, pick 5 or 10 seconds and an aspect ratio, and click Start. The MP4 is in the Output tab after about a minute.

How do I turn a picture into a video?

Paste a direct link to the picture in Start image URL and describe how it moves. The picture becomes the first frame of the video.

Does the video have sound?

Yes. LTX-2.5 generates the sound with the picture: ambience, effects and music that fit the scene. Describe the sound in the prompt to steer it.

How much does an AI video cost?

$0.096 for 5 seconds and $0.116 for 10 seconds, at any aspect ratio. Videos stopped before generation starts cost nothing.

Is there a free AI video generator?

On Apify's free plan you can make 1 five-second video per day, up to 10 per month. Paid Apify plans lift the limit.

Do I need an API key or a GPU?

No. You need only an Apify account. The Actor runs the model for you.

Which is better, LTX-2.5 or MiniMax H3?

LTX-2.5 is fast and cheap, good for social clips, B-roll and drafts. MiniMax H3 gives more detailed, more realistic motion, and keeps a product or a character consistent from reference images. It costs about twice as much ($0.205 per 5 s in HD, $0.133 in SD).

Can I make vertical videos for TikTok and Reels?

Yes. Set the aspect ratio to 9:16 for a 768 × 1344 video.

Can I make several videos at once?

Yes. Put up to 10 objects in Batch of videos. For more, start several runs.

Can I use the videos commercially?

The videos are yours to use. Check that your prompt and start image don't copy someone else's brand, character or likeness.

What content is not allowed?

Don't ask for sexual content, graphic violence or videos of real public figures. Such prompts may be refused; a prompt refused before generation starts is not charged.

How long are the videos kept?

In your run's key-value store, for as long as your Apify plan keeps storage (unnamed run storage is kept for your plan's data retention period, 7 days on the free plan). Download the files you want to keep.

Can I make a 30-second or 1-minute AI video?

Not in one clip: each video is 5 or 10 seconds. Generate several clips (a batch keeps them in one run) and join them in any video editor.

What resolution are the videos? Is it 1080p or 4K?

Up to 1344 × 768 (16:9), 768 × 1344 (9:16) or 960 × 960 (1:1), at 24 fps. That is between 720p and 1080p. There is no watermark.

Can I add my own voiceover or music?

No. The sound is generated with the picture; you can steer it in the prompt ("soft piano music", "crowd cheering"). Add your own audio in a video editor.

Is it an alternative to Runway, Kling, Sora or Veo?

For short clips, yes: you pay per video with no subscription, and you can call it as an API. Those tools offer longer videos and editing features this Actor does not have.

Can I use it from ChatGPT, Claude or another AI agent?

Yes. Every Apify Actor is available through the Apify MCP server, so an AI agent can generate videos with it.

Why did a video fail?

The error field says why: a start image that could not be downloaded or read, a prompt that was refused, or a service that was busy. A video that failed before its generation started is not charged; one that failed after is, and the error says which.

Support / feedback

Found a problem or need a feature? Open an issue on the Issues tab. We usually answer within a day.