Vast Model Library
Access 1000+ image, video, audio, and language models from one unified platform with one API key.
One platform · 1000+ models
Ultimate AI generation
with wavespeed
Bring image, video, audio, and language generation together in one fast creative workspace — built to help you make more and scale without limits. 1000+ AI models. Create faster, scale without limits.
The right model for every idea
Featured Models
One API and one creative home for the latest image, video, audio, and multimodal models.
seedance-2.5/image-to-video
bytedance
image-to-video
seedance-2.5/video-edit
bytedance
video-to-video
seedance-2.5/video-edit-turbo
bytedance
video-to-video
wan-3.0-prime/image-to-video
alibaba
image-to-video
wan-3.0-prime/reference-to-video
alibaba
image-to-video
wan-3.0-prime/text-to-video
alibaba
text-to-video
minimax-h3/image-to-video-spicy
wavespeed-ai
image-to-video
qwen-image-3.0/edit
qwen
image-to-image
flux-3/text-to-image
black-forest-labs
text-to-image
clarity-ai/crystal-video-upscaler
clarity-ai
video-upscaler
A toolkit for every workflow
Get any tool you want
Meshy 3D Models
v7/text-to-3d
v7/multi-image-to-3d
v7/image-to-3d
GPT Image Models
flare/text-to-image
flare/edit
sunburst/text-to-image
Z-Image Models
lora-trainer
controlnet
image-to-image
ElevenLabs AI Models
music-v2.5
music-v2
eleven-v3
Krea 2 Models
turbo
turbo-lora
large/text-to-image
Wan 3.0 Models
prime/image-to-video
prime/text-to-video
prime/reference-to-video
Seedance Models
talking-avatar
image-to-video
video-edit
VEED AI Models
subtitles
lipsync-v2
fabric-1.0
Meshy 3D Models
v7/text-to-3d
v7/multi-image-to-3d
v7/image-to-3d
GPT Image Models
flare/text-to-image
flare/edit
sunburst/text-to-image
Z-Image Models
lora-trainer
controlnet
image-to-image
ElevenLabs AI Models
music-v2.5
music-v2
eleven-v3
Krea 2 Models
turbo
turbo-lora
large/text-to-image
Wan 3.0 Models
prime/image-to-video
prime/text-to-video
prime/reference-to-video
Seedance Models
talking-avatar
image-to-video
video-edit
VEED AI Models
subtitles
lipsync-v2
fabric-1.0
Video Extend
27 models
Object Detection and Segmentation
17 models
Content Detection Models
11 models
LoRA Generation
68 models
Generate Music
34 models
First and Last Frame Video
33 models
Remove Anything
22 models
Ship ideas, not infrastructure
Built For Developers
Integrate any model with one API call. Node, Python, or cURL — move from concept to production in minutes, not days.
image.tsvideo.tsspeech.tschat.ts
1const apiKey = process.env.WAVESPEED_API_KEY
2const response = await createGeneration({
3 model: "image-generator",
4 prompt: "luminous glass sculpture",
5 size: "2048x1152"
6})
8return response.output
10✓ generation complete
Generated output · 2048 × 1152 · PNG
Make from anywhere
And For Creators
Wavespeed Desktop brings the full power of AI media generation to your workspace — no setup, no scattered tools, just create.
Everything in one fast layer
Engineered for Velocity
wavespeed is an AI media generation platform that is easy to use, affordable, scalable, and fast.
Blazing Fast Inference
Optimized GPU clusters deliver rapid image generation and fast video rendering without the usual wait.
Built for Scale
From a single image to millions of requests — reliable infrastructure that grows with your creative workload.
Security
Security-focused infrastructure with encryption and private deployment options for teams that need control.
What people are saying
Northstar
“Everyone wants faster, cheaper, and more flexible AI media generation. wavespeed helps our creative team stay competitive without slowing down.”
Creative OperationsNorthstar Studio
Novita
“Our inference workflow is more efficient, our video costs are lower, and the experience is far more reliable at scale.”
Production TeamNovita AI Lab
SignalBook
“The platform lives up to its name — the models are fast, and the whole team can move from an idea to an output in one place.”
Studio LeadSignalBook
