An audio-to-video agent powered by the LTX-2 19B Distilled model. This agent generates high-quality cinematic video synchronized to your audio inputs using text prompts and optional image frames. Your request will cost $0.00088 per megapixel of generated video data (width × height × frames), rounded up; for example, a 121-frame video at 1280 × 720 costs approximately $0.09856.