Audio to Video with LoRA

Generate high-quality video with audio from audio, text and images using LTX-2.3 and custom LoRA

Inference

Commercial use

Input

Form

Prompt*

crtanim, little guy singing in crt style animation

Type # to reference inputs.

Audio URL*

Add Audio

Hint: Drag and drop audio files from your computer, audio from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: mp3, ogg, wav, m4a, aac

Image URL

Add Image

Hint: Drag and drop image files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL. Accepted file types: jpg, jpeg, png, webp, gif, avif

Match Audio Length

Number of Frames

Resolution

Auto×

Generate Audio

LoRAs*

Path*

Scale

Transformer

both

Add item

Additional Settings

More

Customize your input with more control.

Result

Idle

Preview JSON

What would you like to do next?

Download

{
  "video": {
    "url": "https://v3b.fal.media/files/b/0a9c994e/DGtMIQesw-nUSv5PBBk9S_96202a9aba194d69ad77fd497f3f95e0.mp4",
    "content_type": "video/mp4",
    "file_name": "96202a9aba194d69ad77fd497f3f95e0.mp4",
    "file_size": 2098586
  },
  "seed": 1193146169,
  "prompt": "Style: crtanim, vintage monochrome green CRT monitor - A pixelated young male character stands in the center of a command-line interface, holding a microphone as his mouth opens and closes in perfect synchronization with the singing audio. His head bobs up and down to the rhythm, and his free hand clenches into a fist, pumping slightly with the beat of the music. The green phosphor display flickers with subtle scanlines and a slight curvature of the screen, while the surrounding text remains static as he performs. His eyes widen and his pixelated brows lift during higher notes, his mouth forming round \"O\" shapes and wide \"A\" shapes as the lyrics progress. With every rhythmic pulse in the audio, a faint glow emanates from the character's sprite, causing a blooming effect on the dark glass of the monitor."
}

Your request will cost $0.0027075 per megapixel of generated video data (width × height × frames), rounded up. For example, if you generate a video that is 121 frames long at 1280 × 720, your total generated video is ≈112 MP, and your request will cost $0.3032.