---
title: "Detect human body poses"
method: POST
path: "/v1/apple/body-pose"
tags: ["Apple"]
---

# Detect human body poses

`POST /v1/apple/body-pose`

## Request

- Base URL: `http://localhost:9998`
- URL: `http://localhost:9998/v1/apple/body-pose`
- Auth: HTTP bearer

Detects skeletal keypoints using Apple Vision (Swift-native API).
Joint names use camelCase (nose, neck, leftShoulder, rightElbow, etc.).
Coordinates are normalized 0–1, top-left origin (y=0 is top of image).

## Request body

- ImageRequest
  - `image` string, required: Base64-encoded image data (PNG, JPEG, TIFF, HEIC)

## Response `200`

Detected body poses

- object
  - `bodies` PoseResult[]
    - `joints` object

## Other responses

- `400`: Invalid request

---

[API](https://skmtc.dev/modelpiper/apis/toolpiper-api.md) · [All operations](https://skmtc.dev/modelpiper/apis/toolpiper-api/llms.txt) · [OpenAPI document](https://skmtc.dev/modelpiper/apis/toolpiper-api/revisions/6722bf56385c?raw)