▣ ARTIFICIAL INTELLIGENCE · SMART GENERATION

Generate Text to Video With LTX Video (RTX 5080)

What it does

Text to Video Generator turns a text prompt into a short MP4 video using LTX video generation. Send a prompt, and you can optionally tune cfg, seed, steps, width, height, length, and negative_prompt to control guidance, reproducibility, frame count, and output size.

The POST /ltx/generate endpoint starts a generation task and returns a status, message, and task_id. Use GET /tasks/:task_id to check progress until the job reaches completed or error. When the video is ready, the task status response includes an output_url to the finished MP4.

Use Text to Video Generator when you need short motion clips from a script, product concept, storyboard note, or scene description. It is a fit for prototyping video ideas, creating demo assets, or generating synthetic motion content without a manual editing workflow.

Because the output is task-based, you can kick off generation and poll asynchronously while your app continues other work. That makes it easy to slot into content pipelines, creative tools, or internal review systems where you need a generated clip and a reliable completion signal.

Notes: Text-to-video with LTX-Video 13B (distilled) on a dedicated NVIDIA RTX 5080. Generates a ~4-second cinematic clip in ~30 seconds.

▣ ENDPOINT 01 / 02

POST

Generate a short video (LTX, RTX 5080)

https://api.eu.apyhub.com/mastera-ai/ltx-video-rtx-5080/v1/ltx/generate

QUICKSTART

GUIDE

Quickstart

Start a text-to-video generation job with a prompt.

curl -X POST "https://api.eu.apyhub.com/mastera-ai/ltx-video-rtx-5080/v1/ltx/generate" \
  -H 'apy-token: $APY_TOKEN' \
  -H 'Content-Type: application/json' \
  -d '{
    "prompt": "Ocean waves at sunset, cinematic, slow camera pan",
    "negative_prompt": "",
    "width": 768,
    "height": 512,
    "length": 97,
    "steps": 8,
    "cfg": 1
  }'

What you'll get back

Returns a JSON object with status (string), message (string), and task_id (string) fields. status indicates the job state, message provides a human-readable note, and task_id is the identifier for the queued generation task.

{
  "task_id": "61442d82a33e",
  "status": "processing",
  "message": "Video generation started. Poll GET /v1/tasks/{task_id} for result."
}

TRY ITLIVE · 7200 ATOMS

API key

Loading your default key…

The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.

About this endpoint

What it does

Generates a short video from a text prompt and starts the job asynchronously. The request body contains the generation settings, and the response returns a task identifier you can use to track the job.

Request Body

Parameter	Type	Mandatory	Description
prompt	String	Yes	The text description of the video to generate.
cfg	Number	No	Guidance scale. Default: `1`. `1.0` is recommended for the distilled model.
seed	Integer	No	Random seed for reproducible generation. Default: `0`.
steps	Integer	No	Number of inference steps. Default: `8`. Minimum: `1`. Maximum: `15`.
width	Integer	No	Output video width in pixels. Default: `768`. Minimum: `256`. Maximum: `1024`.
height	Integer	No	Output video height in pixels. Default: `512`. Minimum: `256`. Maximum: `1024`.
length	Integer	No	Video duration in frames at 25 fps. Default: `97`. Minimum: `9`. Maximum: `161`. Snapped to a valid `n*8+1` value.
negative_prompt	String	No	What to avoid in the generated video. Default: `""`.

Response

Returns a JSON object with status, message, and task_id string fields. The task_id field contains the identifier for the asynchronous job.

Parameter	Type	Mandatory	Description
status	String	No	Job status.
message	String	No	Additional message about the request or job.
task_id	String	No	The job identifier to use when checking progress.

Notes

This endpoint kicks off an async job and returns immediately with a job identifier; the actual work runs in the background. Pair this call with the corresponding job_check endpoint — poll that until the status reaches a terminal state to retrieve the result. Extract the job id from task_id.

Body

Name

Type

Description

bodyREQUIRED

object

—

▣ ENDPOINT 02 / 02

GET

Poll LTX video status (RTX 5080)

https://api.eu.apyhub.com/mastera-ai/ltx-video-rtx-5080/v1/tasks/:task_id

QUICKSTART

GUIDE

Quickstart

Check the status of a video-generation task by its task_id.

curl "https://api.eu.apyhub.com/mastera-ai/ltx-video-rtx-5080/v1/tasks/:task_id" \
  -H 'apy-token: $APY_TOKEN'

What you'll get back

Returns a JSON object with these top-level fields when available: type (string), error (string), status (string), message (string), task_id (string), and output_url (string).

{
  "type": "ltx_t2v",
  "status": "completed",
  "task_id": "task-123",
  "output_url": "https://example.com/video.mp4"
}

TRY ITLIVE · 1 ATOM

API key

Loading your default key…

The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.

About this endpoint

What it does

Polls the status of an LTX text-to-video task using the task identifier in the path. The response reports the task’s current status and may include the finished video URL once the task is completed.

Path Parameter(s)

Attribute	Type	Mandatory	Description
task_id	String	Yes	Identifies the video generation task.

Response

Returns a JSON object with type, error, status, message, task_id, and output_url fields. The status field indicates the current task state, and output_url is the URL to the finished MP4 when status is completed.

Parameter	Type	Mandatory	Description
type	String	No	Task type.
error	String	No	Error message, if present.
status	ENUM	No	Current task status. Allowed values: `processing`, `generating`, `completed`, `error`.
message	String	No	Additional status message.
task_id	String	No	Task identifier.
output_url	String	No	URL to the finished MP4, only when `status` is `completed`.

Path parameters

Name

Type

Description

task_idREQUIRED

string

—

▣ COMMON ERRORS

Errors any endpoint can return

400bad_request

Required parameter missing or malformed body.

401unauthorized

API key missing, revoked, or not authorized for this service.

429rate_limited

Your plan's per-second rate exceeded. Retry with exponential backoff.

503upstream_busy

Backend temporarily unavailable. Try again in a few seconds.