Build end‑to‑end
AI 3D workflows with Mugen3D API
One surface for 3D generation, digital humans, audio-driven facial animation, and realtime rendering — built for production.
# Audio → Face mesh (MugenMorph)
curl -X POST https://api.sumeruai.us/v1/audio-to-face/mesh \
-H "Authorization: Bearer YOUR_ACCESS_TOKEN" \
-H "Content-Type: application/json" \
-H "Accept: application/x-protobuf" \
-d '{
"traceId": "16a9c837-9a12-4a11-bdad-a0b363287ea1",
"status": "start",
"data": "UklGRiQAAABXQVZFZm10IBAAAA..."
}'Any image, any idea — 3D in one call.
From REST to native SDKs — ship in the language you already use. Move from prototype to production in minutes.
import requests
def submit_mugen_sq(access_token: str, image_path: str):
url = "https://api.sumeruai.us/v1/mugen-3d/sq"
headers = {"Authorization": f"Bearer {access_token}"}
with open(image_path, "rb") as f:
files = {"file": f}
return requests.post(url, headers=headers, files=files).json()
result = submit_mugen_sq("YOUR_ACCESS_TOKEN", "/path/to/image.jpg")
print("Task ID:", result["data"]["id"])Core APIs, ready to call
Where geometry becomes a living world
Generate characters, props, and worlds with AI, bringing stories to life through real-time interaction.
Go beyond fixed camera angles with interactive characters, flexible viewpoints, and real-time conversations.
Turn landmarks, artifacts, and exhibitions into explorable 3D experiences that bring cultural heritage to life.
Make learning more immersive with interactive 3D content, virtual instructors, and simulated environments.
Reconstruct real environments in high-fidelity 3D to support robotic perception, navigation, and simulation.
Turn images into 3D models, then prepare them for printing through mesh conversion and post-processing.
Built for production
Global edge, P95 < 900ms.
No polling for long jobs.
Key isolation, audit logs, SOC 2 ready.
Pay by the second / frame. No minimums.
Frequently asked
Something else on your mind? Email service@sumeruai.com — we usually reply within one working day.