Skip to content

AI Models on Pixo

Pixo runs 47 AI models from 13 creators — video, image, voice, music, lip-sync and more. Mix any of them inside a single project, on one bill.

Video · 20

Text-to-video and image-to-video. Combine models freely across shots in one storyboard.

Seedance · ByteDance

ModelResolutionLengthAspect ratiosNative audioReference inputs
Seedance 1 Pro Fast480p · 720p · 1080p2–12s16:9 · 4:3 · 1:1 · 3:4 · 9:16 · 21:9——
Seedance 1.5 Pro480p · 720p · 1080p4–12s16:9 · 4:3 · 1:1 · 3:4 · 9:16 · 21:9Yes—
Seedance 2.0480p · 720p · 1080p · 4k4–15s16:9 · 4:3 · 1:1 · 3:4 · 9:16 · 21:9Yes9 images, 3 videos, 3 audio
Seedance 2.0 Fast480p · 720p4–15s16:9 · 4:3 · 1:1 · 3:4 · 9:16 · 21:9Yes9 images, 3 videos, 3 audio
Seedance 2.0 Mini480p · 720p4–15s16:9 · 4:3 · 1:1 · 3:4 · 9:16 · 21:9Yes9 images, 3 videos, 3 audio

Kling · Kuaishou

ModelResolutionLengthAspect ratiosNative audioReference inputs
Kling 3.0720p · 1080p3–15s16:9 · 9:16 · 1:1Yes—
Kling 3.0 Omni720p · 1080p3–15s16:9 · 9:16 · 1:1Yes7 images
Kling 3.0 Turbo720p · 1080p3–15s16:9 · 9:16 · 1:1——

Hailuo · MiniMax

ModelResolutionLengthAspect ratiosNative audioReference inputs
Hailuo 2.3768p · 1080p6–10s———
Hailuo 2.3 Fast768p · 1080p6–10s———

Sora · OpenAI

ModelResolutionLengthAspect ratiosNative audioReference inputs
Sora 2—4–12s16:9 · 9:16—1 image
Sora 2 Pro720p · 1080p4–12s16:9 · 9:16—1 image

VEO · Google

ModelResolutionLengthAspect ratiosNative audioReference inputs
VEO 3.1720p · 1080p · 4k4–8s16:9 · 9:16—3 images
VEO 3.1 Fast720p · 1080p · 4k4–8s16:9 · 9:16——

Other video models

ModelCreatorResolutionLengthAspect ratiosNative audioReference inputs
Grok Imagine VideoxAI720p · 480p1–15s16:9 · 4:3 · 1:1 · 9:16 · 3:4 · 3:2 · 2:3——
LatentSyncByteDance—————
LTX 2.3 ProLightricks1080p · 2k · 4k6–10s16:9 · 9:16Yes—
Omni Human 1.5ByteDance—————
Pixverse V4.5PixVerse540p · 720p · 1080p5–8s16:9 · 9:16 · 4:3 · 3:4 · 1:1 · 21:9——
WAN 2.6WAN720p · 1080p5–15s16:9 · 9:16——

Image · 7

Stills, character and style references, and image editing.

ModelCreatorResolutionAspect ratiosReference inputs
Nano BananaGoogle—1:1 · 2:3 · 3:2 · 3:4 · 4:3 · 4:5 · 5:4 · 9:16 · 16:9 · 21:9—
Nano Banana ProGoogle1 MP · 2 MP · 4 MP1:1 · 2:3 · 3:2 · 3:4 · 4:3 · 4:5 · 5:4 · 9:16 · 16:9 · 21:9—
Nano Banana 2Google1K · 2K · 4K1:1 · 1:4 · 1:8 · 2:3 · 3:2 · 3:4 · 4:1 · 4:3 · 4:5 · 5:4 · 8:1 · 9:16 · 16:9 · 21:9—
Seedream 4.5ByteDance2 MP · 4 MPmatch_input_image · 1:1 · 4:3 · 3:4 · 16:9 · 9:16 · 3:2 · 2:3 · 21:9—
Grok Imagine ImagexAI1k · 2k1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 2:1 · 1:2 · 19.5:9 · 9:19.5 · 20:9 · 9:20 · auto—
Grok Imagine Image ProxAI1k · 2k1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 2:1 · 1:2 · 19.5:9 · 9:19.5 · 20:9 · 9:20 · auto—
GPT Image 2OpenAI—1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 4:5 · custom4 images

Voice · 7

Text-to-speech and voice cloning for narration and dialogue.

ModelCreatorVoicesLanguages
Minimax Speech 02 HDMiniMax30243
Minimax Speech 02 TurboMiniMax30243
Minimax Voice CloningMiniMax——
ElevenLabs v3 AlphaElevenLabs43—
ElevenLabs Multilingual v2ElevenLabs43—
ElevenLabs Turbo v2.5ElevenLabs43—
ElevenLabs Flash v2.5ElevenLabs43—

Text · 6

Scriptwriting and copy generation inside the playground.

ModelCreator
GPT-4o MiniOpenAI
Gemini 2.5 FlashGoogle
Gemini 3.1 ProGoogle
DeepSeek V3DeepSeek
DeepSeek R1DeepSeek
Doubao Seed 1.6ByteDance

Music · 3

Original scoring and background tracks.

ModelCreatorLength
ElevenLabs MusicElevenLabs10–300s
Minimax Music 2.5MiniMax—
Stable Audio 2.5Stability AI1–190s

Lip-sync · 2

Match an existing video to a voice track.

ModelCreatorInputs
React 1Sync LabsVideo + Audio
Omni HumanByteDanceAudio

Sound effects · 1

Generate sound effects from a text description.

Runs on ElevenLabs Sound Effects, by ElevenLabs.

Transcription · 1

Turn speech in audio or video into text.

Runs on Whisper Large V3, by OpenAI.