Synthesis AI
Synthesis AI was a San Francisco synthetic-data company, founded in 2019 by Yashar Behzadi, that generated photorealistic, pixel-perfectly labeled images of humans for training computer-vision models. It sold that capability as an API: FaceAPI for labeled facial imagery and, from November 2021, HumanAPI for whole-body 3D digital humans, plus an Identities API for selecting subjects. Jobs were described as JSON documents (identities, expressions, gaze, head turn, hair, accessories, bodies and clothing, gesture animations, camera and light rigs, HDRI environments) and submitted through a command-line client or web console, with rendered output downloaded by job ID. The company raised a $17M Series A in 2022 on more than $24M total funding and was dissolved during 2024-2025. Its API is gone: synthesis.ai is a parked Gandi holding page reachable only over HTTP, and docs.synthesis.ai and api.synthesis.ai no longer resolve. What survives publicly is the Synthesis-AI-Dev GitHub organization (17 public repositories, including the Human API input-JSON appendix and the client tooling) and the official synthesisai package on PyPI.
Synthesis AI is profiled on the APIs.io network. Tagged areas include Company, Synthetic Data, Computer Vision, Machine Learning, and Artificial Intelligence.
Synthesis AI’s developer surface includes code examples and 7 more developer resources.
Kin Score
Examples 1
Example request and response payloads for these APIs.
Security Posture 1
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Resources
Design & Contract 1
Pagination, idempotency, versioning, errors, and events
Build 3
SDKs, sample code, and the tooling you integrate with
Access & Security 1
Authentication, authorization, and security posture
Company 2
The organization behind the API
Other 1
Properties that don't map to a standard resource type