LTX 2.5 Fast Text to Video API

POST Base URL: https://api.hiapi.ai /v1/tasks

Image, video, and audio models are called through theUnified Async API POST /v1/tasks endpoint; only the input fields differ (see input parameters below).

Model summary

Model	ltx-2.5-fast/text-to-video
Capability	Text-to-video + native audio
Resolution	720p / 1080p
Duration	2-20 seconds

Turn a text prompt into a 2-20 second 720p or 1080p video, landscape or vertical, with native audio. Billed per second.

Production guidance

Calling the API

Draft at 720p with a short duration, then switch to 1080p or a longer clip for the final cut.
Set aspect_ratio=9:16 for vertical short-form video.
Use callback.url for task notifications; read the task object from data in query responses and directly from the callback body.
Artifact URLs expire; copy files you need to keep into persistent storage.

Best suited for

Ads and product shots

Describe subject, action and sound in one prompt for an edit-ready shot.

promptgenerate_audio

Vertical social content

9:16 output for short-video platforms.

aspect_ratio

Long takes and previz

Up to 20 seconds for continuous action and storyboard previews.

durationresolution

Request parameters

POST https://api.hiapi.ai/v1/tasks

# Create an async task — returns taskId immediately (generation runs async)
# Replace YOUR_API_KEY with your account API key
curl -X POST "https://api.hiapi.ai/v1/tasks" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ltx-2.5-fast/text-to-video",
  "input": {
    "prompt": "A barista pours steamed milk into a latte, creating a leaf pattern, close-up, soft morning light through a café window, gentle clinking cups and café ambience",
    "resolution": "720p",
    "duration": 6,
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}'

import requests, json

# Business params — fields vary by model (see the model page)
payload = json.loads(r'''
{
  "model": "ltx-2.5-fast/text-to-video",
  "input": {
    "prompt": "A barista pours steamed milk into a latte, creating a leaf pattern, close-up, soft morning light through a café window, gentle clinking cups and café ambience",
    "resolution": "720p",
    "duration": 6,
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}
''')

# Create an async task — returns taskId immediately (generation runs async)
resp = requests.post(
    "https://api.hiapi.ai/v1/tasks",
    headers={"Authorization": "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
    json=payload,
)
print(resp.json())  # Returns { code, message, data: { taskId } }

// Create an async task — returns taskId immediately (generation runs async)
// Replace YOUR_API_KEY with your account API key
const resp = await fetch("https://api.hiapi.ai/v1/tasks", {
  method: "POST",
  headers: {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
  "model": "ltx-2.5-fast/text-to-video",
  "input": {
    "prompt": "A barista pours steamed milk into a latte, creating a leaf pattern, close-up, soft morning light through a café window, gentle clinking cups and café ambience",
    "resolution": "720p",
    "duration": 6,
    "aspect_ratio": "16:9",
    "generate_audio": true
  }
}),
});
console.log(await resp.json()); // Returns { code, message, data: { taskId } }

model string required

Model ID.

example ltx-2.5-fast/text-to-video

input object required

Text-to-video parameters.

prompt string required

Describe the scene, action, camera and sound. Up to 5,000 characters.

resolution enum optional

Output resolution; sets the per-second price.

default 720p enum: 720p1080p

duration enum optional

Length in seconds: 2-6, 8, 10, 12, 14, 16, 18 or 20. Billed per second.

default 6 enum: 234568101214161820

aspect_ratio enum optional

Landscape 16:9 or vertical 9:16.

default 16:9 enum: 16:99:16

generate_audio boolean optional

Generate native audio (ambience, effects, music) with the video. Does not change the price.

default true

callback object optional

Sends a notification when the task succeeds or fails; read the task object from data in query responses and directly from the callback body.

url string required

HTTPS URL that receives task success or failure notifications.

example https://your-domain.com/hiapi/callback

when enum optional

Triggers when the task succeeds or fails.

default final enum: final

Example requests

Landscape clip with sound

Defaults: 720p, 6 s, 16:9, native audio.

Request body

{
  "model": "ltx-2.5-fast/text-to-video",
  "input": {
    "prompt": "A barista pours steamed milk into a latte, creating a leaf pattern, close-up, soft morning light through a café window, gentle clinking cups and café ambience"
  }
}

1080p vertical

Vertical 1080p, 4 seconds.

Request body

{
  "model": "ltx-2.5-fast/text-to-video",
  "input": {
    "prompt": "A skateboarder carves down an empty coastal road at sunset, tracking shot from behind",
    "resolution": "1080p",
    "aspect_ratio": "9:16",
    "duration": 4
  }
}

Getting the result

Read data.taskId from the create-task response.
Wait for the callback or query GET /v1/tasks/:id; polling puts the task under data.
When status=success, read the video URL from output type=video; a callback reads output directly.

FAQ

Which resolutions and lengths are supported?

720p and 1080p; 2-20 seconds: 2, 3, 4, 5, 6, 8, 10, 12, 14, 16, 18 or 20.

Is it cheaper with generate_audio off?

No. Price depends only on resolution and duration; audio is not priced.

Can I start from an image?

Yes. Use ltx-2.5-fast/image-to-video and pass the first frame (and an optional last frame) in image_urls.

Can I change the frame rate?

It is fixed at 25fps; no parameter is needed.