LTX 2.3: the audio-to-video AI model

LTX 2.3 is an AI video generation model from LTX. It supports text-to-video, image-to-video, and audio-to-video generation. With audio-to-video, you provide an audio track and LTX 2.3 generates visuals synchronized to it

LTX 2.3 can use an audio track to generate the video itself, rather than only matching mouth movements to existing footage. Dialogue, music, or ambient sound can be used as the input, with the generated visuals synchronized to the audio.

LTX supports WAV, MP3, M4A, and OGG audio files. You can also provide an image to use as the first frame and a text prompt to describe the video or guide how that image should be animated.

LTX 2.3 comes in Fast and Pro variants. Fast is designed for faster generation and supports text-to-video and image-to-video. Pro supports those modes as well as audio-to-video and additional video editing capabilities. Audio-to-video with LTX 2.3 is available through the Pro model.

LTX 2.3 supports portrait and landscape video, with resolutions up to 4K depending on the generation mode. It also supports native 9:16 vertical video generation.

Seedance 2.5 supports 20 languages with matched lip-sync, and can localize the setting, characters, and dialogue so one production works for audiences worldwide.

Seedance 2.5 doubles clip length to 30 seconds, replaces 2.0's over-saturated glow with softer, physics-accurate lighting and more natural eye and facial detail, adds realistic impact physics and 3D-reference texturing, and raises reference support from 15 to 50.

Yes. Videos created through Picsart's tools powered by Seedance 2.5 can be used for marketing, social media, brand content, and other commercial applications, subject to Picsart's terms of use.