AI Models on Veevid

Every video, image and voice model you can use on Veevid, in one place. Pick a model to see what it can do and start creating.

AI Video Models

Kling 4.0
3 to 30 second single-shot videos in up to 4K, with stereo audio and accurate lip sync.
Kling 3.0
4K cinematic videos up to 15 seconds, with multi-shot directing and native audio.
Seedance 2.5
30-second single-take videos in native 1080p, with up to 50 references plus editing and extension.
Seedance 2.0
Text, image, audio and video inputs, with picture and sound generated together.
Wan 3.0
30-second videos from text, images, clips, audio or a PDF, with native sound on every render.
Wan 2.7
Text-to-video, image-to-video with first and last frame control, reference-to-video and video editing.
LTX 2.5
6 to 20 second videos in up to 4K, with dialogue and sound generated together.
LTX 2.3
4K videos up to 20 seconds: Fast Flow for speed, Pro Flow for quality.
MiniMax H3 Max
5 to 15 second videos up to 1080p, with synchronized audio and first and last frame control.
MiniMax H3
2K video from text, images, clips and audio, with native stereo audio.
Gemini Omni
Mix up to 7 reference images or guide the motion with a clip. Native audio, 720p to 4K.
Grok Imagine
6 to 30 second videos in several styles, with automatic audio sync and reference-guided generation.
Creatify Boreal
1 to 20 second ads, UGC clips and presenter videos, with dialogue and music generated with the picture.

AI Image Models

AI Voice Models

E
Eleven v4
Expressive AI voiceovers you can direct with audio tags like [whispers] and [laughs].