---
title: "Start inference debug stream"
method: POST
path: "/api/{projectId}/device/{deviceId}/debug-stream/inference/start"
tags: ["Devices"]
---

# Start inference debug stream

`POST /api/{projectId}/device/{deviceId}/debug-stream/inference/start`

## Request

- Base URL: `https://studio.edgeimpulse.com/v1`
- URL: `https://studio.edgeimpulse.com/v1/api/{projectId}/device/{deviceId}/debug-stream/inference/start`
- Auth: one of:
  - API key in header `x-api-key`
  - API key in cookie `jwt`
  - API key in header `x-jwt-token`
  - OAuth 2
    - Authorization code: `/v1/oauth/authorize`
    - Client credentials
    - Implicit: `/v1/oauth/authorize`
    - Password
    - Token URL: `/v1/oauth/token`
- TypeScript: <https://skmtc.dev/edgeimpulse/apis/edge-impulse-api/docs/api/:projectId/device/:deviceId/debug-stream/inference/start/post.ts> (a function with typed inputs; its response is checked against the schema)

Start an inference debug stream for this device with inference results (and images if a camera is attached). Updates are streamed through the websocket API. A keep-alive token is returned, you'll need to ping the API (with keepDeviceDebugStreamAlive) every 10 seconds (so we know when the client is disconnected).

## Path parameters

- `projectId` integer, required
- `deviceId` string, required

## Response `200`

OK

- StartDeviceDebugStreamResponse
  - `success` boolean, required: Whether the operation succeeded
  - `error` string: Optional error description (set if 'success' was false)
  - `streamId` integer, required

---

[API](https://skmtc.dev/edgeimpulse/apis/edge-impulse-api.md) - [All operations](https://skmtc.dev/edgeimpulse/apis/edge-impulse-api/llms.txt) - [OpenAPI document](https://skmtc.dev/edgeimpulse/apis/edge-impulse-api/revisions/e2a976d38427?raw)