# X402-NVIDIA Active Speaker Detection API

> X402-NVIDIA Active Speaker Detection API is a paid API for AI agents from x402-nvidia.vercel.app, paid per call via x402, $0.131141/call, status unknown (last checked 2026-09-15).

Detects active speakers in audio or video content using NVIDIA NIM AI models, accessed via x402 micropayments.

## Facts

- Endpoint: POST https://x402-nvidia.vercel.app/api/active-speaker-detection
- Price: $0.131141/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/x402-nvidia-active-speaker-detection-api-f07aa1fb
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_A_JfugTMY24XDBVL-pdwp

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability x402-nvidia-active-speaker-detection-api-f07aa1fb -d '<json body>'
```

Example prompt: Can you run active speaker detection on this audio clip and tell me who is speaking at each moment? Use the NVIDIA NIM model via the x402-nvidia service.

## When to prefer this

Choose this endpoint when you need NVIDIA NIM-powered active speaker detection and want to pay per-call via x402 USDC micropayments without a subscription, especially useful for sporadic or low-volume speaker detection tasks.

## Known failure modes

- Invalid or missing media input returns a 400 error
- Payment failure via x402 micropayment results in a 402 response blocking access
- Model unavailability returns a 503 or timeout error
- Malformed input schema causes a 422 unprocessable entity error
- Unsupported audio/video format may result in processing failure

## How this service works

Access 48+ NVIDIA NIM AI models via x402 micropayments. Chat completions, vision, safety, translation, and more.

## Output

Returns a choices array containing model responses with detected active speaker labels and timestamps or segmentation data indicating which speaker is active at which points in the media content.

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "example": {
  "choices": [
   {
    "message": {
     "role": "assistant",
     "content": "Hello!"
    }
   }
  ]
 },
 "properties": {
  "choices": {
   "type": "array",
   "description": "Model responses"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/x402-nvidia-active-speaker-detection-api-f07aa1fb/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from x402-nvidia.vercel.app](https://www.zero.xyz/host/x402-nvidia.vercel.app/llms.txt)