Skip to main content
Model ID 
ltx-2-pro-audio-to-video

​
LTX-2 Pro Audio-to-Video API Usage Guide

​
Overview

LTX-2 Pro Audio-to-Video generates a video from an audio file using the LTX-2 Pro model. Optionally provide an image as the first frame and a text prompt to guide visual generation. The output video duration matches the audio length (2-20 seconds). It operates synchronously and returns the video directly.

​
Key Features:

  • Synchronous Operation: Results returned directly
  • Audio-Driven: Video content and timing match the audio
  • Optional Image Input: Use an image as the first frame
  • Optional Prompt: Guide visual generation with text
  • Resolution: 1080p only
  • Duration: Determined by audio length (2-20 seconds)

​
Authentication

All API requests require authentication. Include your API key in the Authorization header: 
Authorization: Bearer YOUR_API_KEY

​
Submit Request

​
Endpoint

POST /api/v1/ie/requestqueue/apikey/requests

​
Request Format

curl -X POST "https://console.gmicloud.ai/api/v1/ie/requestqueue/apikey/requests" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ltx-2-pro-audio-to-video",
    "payload": {
      "audio_uri": "https://example.com/narration.wav",
      "prompt": "Ocean waves crashing on rocky shore at sunset",
      "image_uri": "https://example.com/beach.jpg",
      "resolution": "1920x1080"
    }
  }'

​
Request Parameters

ParameterTypeRequiredDescriptionDefaultConstraints
audio_uriaudioYesAudio file URL. Duration must be 2-20 seconds. Supported: WAV, MP3, MP4, OGG.-Required
promptstringNoText description of the video content. Required if image_uri is not provided.--
image_uriimageNoImage URL for the first frame. If provided, prompt describes how it should be animated.-Max 1 image
resolutionenumNoOutput video resolution.1920x10801080p only
guidance_scalefloatNoHigher values follow the prompt more closely.5 (text), 9 (with image)-

​
Response

{
  "request_id": "abc123",
  "model": "ltx-2-pro-audio-to-video",
  "status": "success",
  "created_at": 1761763441,
  "updated_at": 1761763461
}

​
Check Request Status

​
Endpoint

GET /api/v1/ie/requestqueue/apikey/requests/{request_id}

​
Example

curl -X GET "https://console.gmicloud.ai/api/v1/ie/requestqueue/apikey/requests/{request_id}" \
  -H "Authorization: Bearer YOUR_API_KEY"

​
Response

{
  "request_id": "abc123",
  "model": "ltx-2-pro-audio-to-video",
  "status": "success",
  "payload": {
    "audio_uri": "https://example.com/narration.wav",
    "prompt": "Ocean waves crashing on rocky shore at sunset"
  },
  "outcome": {
    "media_urls": [
      {
        "id": "0",
        "url": "https://storage.googleapis.com/.../video.mp4"
      }
    ]
  },
  "created_at": 1761763441,
  "updated_at": 1761763461,
  "queued_at": 1761763441
}

​
Request Status Values

StatusDescription
queuedRequest is waiting to be processed
processingVideo generation is in progress
successVideo generation completed successfully
failedVideo generation failed
cancelledRequest was cancelled

​
List Your Requests

​
Endpoint

GET /api/v1/ie/requestqueue/apikey/requests?model_id=ltx-2-pro-audio-to-video

​
Get Model Information

​
Endpoint

GET /api/v1/ie/requestqueue/apikey/models/ltx-2-pro-audio-to-video

​
Specifications

SpecificationValue
Modelltx-2-pro
Resolution1080p (1920x1080) only
Duration2-20 seconds (determined by audio length)
Supported audio formatsWAV, MP3, MP4, OGG