LTX 2.5 Audio-Led 4K Video
LTX 2.5 generates video from text, an image or a short audio clip, with synchronized audio, camera controls and output up to 4K in Fast and Pro tiers.
- Ltx
- 6 variants
- From $0.13 per second
- Price
- See price
- Speed
- ~1 min
- Best for
- Lip sync · Voice to Video
- Price
- See price
- Speed
- ~1 min
- Best for
- Text to Video
- Price
- See price
- Speed
- ~1 min
- Best for
- Image to Video
- Price
- See price
- Speed
- ~1 min
- Best for
- Lip sync · Voice to Video
- Price
- See price
- Speed
- ~1 min
- Best for
- Image to Video
- Price
- See price
- Speed
- ~1 min
- Best for
- Text to Video
More from Ltx.
A family groups the versions of one model line. Open one to compare its variants side by side.
Working with LTX 2.5.
LTX 2.5 is Lightricks' current video family and the only one here that treats audio as an input. Audio-to-Video builds synchronized visuals from a short clip of dialogue, music or sound, while the text and image variants add duration, resolution, camera-motion controls and output up to 4K. Each route comes in Fast and Pro.
When to choose LTX 2.5
Choose LTX 2.5 when sound leads the edit — a music cue or a line of dialogue you already have. LTX 2.3 is the older family with 20-second clips and lipsync; Veo and Seedance are the alternatives for prompt-led work.
Choosing between the variants
Fast variants are for iteration, Pro for the finished take. Audio to Video starts from a sound clip, Image to Video from a frame with camera-motion control, and Text to Video from a prompt with flexible duration and up to 4K.
Questions about LTX 2.5
The short answers. For anything specific to your setup, talk to our team.
It generates video synchronized to a short audio clip, optionally guided by an image or prompt, so the visuals follow the sound rather than the reverse.
Up to 4K on the text variant, with 720p and 1080p options on the Pro text-to-video route.
Fast. It carries the same controls with shorter render times, which is what you want while the shot is still changing.





