MASHBOXLabs
Request access

Models

16 open models and pipelines, ours and others'. MASHBOX Creature and MASHBOX Voice are free demos for approved companies; the other 14 are available as Packs.

MASHBOX VoiceRequest access
Model by MASHBOX Labs, built on Maya1 by Maya ResearchLive demoReady to serve

Text to expressive speech in a voice you describe in plain words.

Text to speechtext in, speech out
MASHBOX CreatureRequest access
Pipeline by MASHBOX LabsLive demoReady to serve

One text prompt to a textured, rigged 3D creature as GLB.

Text to 3DRiggingtext in, rigged, textured 3D model (GLB) out
Z-Image Turbo
Model by Tongyi-MAI (Alibaba)Ready to serveExample output

Text to image.

Text to imagetext in, image out
Wan 2.2 Image to Video
Model by Wan team (Alibaba)Ready to serveExample output

An image and a prompt in, a video clip out.

Image to videoimage + text in, video out
Qwen3-30B-A3B
Model by Qwen team (Alibaba)Ready to serveExample output

Chat with streaming, OpenAI-compatible.

Text to texttext in, text out
Llama 3.1 8B Instruct
Model by MetaReady to serve

Chat, OpenAI-compatible.

Text to texttext in, text out
Track2Rig
Model Experimental by MASHBOX LabsReady to serveExample output

3D point tracks of a moving body in; skeleton, skin and bone motion out as GLB.

RiggingMotion3D point tracks in, skeleton, skin and motion (GLB) out
MASHBOX Stride
Model by MASHBOX LabsReady to serveExample output

Describe a movement and get a humanoid motion clip.

Motiontext in, motion clip out
FLUX.2 [klein] 4B
Model by Black Forest LabsReady to serve

Text to image.

Text to imagetext in, image out
TRELLIS.2
Model by MicrosoftReady to serve

An image to a textured 3D model.

Image to 3Dimage in, textured 3D model out
TokenRig
Model by VASTReady to serveExample output

Auto-rig and skin any mesh.

Rigging3D mesh in, rigged mesh out
Audio2Face-3D
Model by NVIDIAReady to serve

Speech audio to facial animation.

Motionspeech audio in, facial animation out
Granite Speech 4.1 2B
Model by IBMReady to serveExample output

Speech to text, OpenAI-compatible.

Speech to textspeech audio in, text out
Z-Image ControlNet Union
Model by Alibaba PAIReady to serveExample output

Images guided by a pose, depth or edge image.

Text to imagetext + control image in, image out
Upscaler
ModelReady to serveExample output

Image and video upscaling.

Upscalingimage or video in, larger image or video out
AniGen
Model by VASTReady to serve

An image to a rigged 3D model.

Image to 3DRiggingimage in, rigged 3D model out