JavaScript SDK
The Overshoot JavaScript SDK lets you run Vision Language Models on live video directly from the browser.
Install
npm install overshootGet an API Key
Get your API key at platform.overshoot.ai/api-keys (opens in a new tab).
Basic Usage
The main class is RealtimeVision. Point it at a video source, provide a prompt, and receive results through the onResult callback.
import { RealtimeVision } from 'overshoot'
const vision = new RealtimeVision({
apiKey: 'your-api-key',
model: 'Qwen/Qwen3.5-9B',
prompt: 'Read any visible text',
source: { type: 'camera', cameraFacing: 'environment' },
onResult: (result) => {
console.log(result.result)
}
})
await vision.start()
await vision.stop()Using a Video File
import { RealtimeVision } from 'overshoot'
const vision = new RealtimeVision({
apiKey: 'your-api-key',
model: 'Qwen/Qwen3.5-9B',
prompt: 'Describe what you see',
source: { type: 'video', file: videoFile },
onResult: (result) => {
console.log(result.result)
}
})
await vision.start()
await vision.stop()Results arrive continuously as the video plays.