Back to Models
N

Active Speaker Detection

NVIDIA
by NVIDIA

Detect and track speaker identities across video frames.

Free EndpointDownloadableApr 16, 2026open license

Specifications

Context Length
8K
8,192 tokens
Input Price
Free
per 1M tokens
Output Price
Free
per 1M tokens
Modalities
2
video→text, audio→text

Capabilities

video analysisaudio

Tags

broadcastspeaker-detectionvideo-analysis

API Usage

1Router is fully OpenAI-compatible. Just set the base URL and use this model ID:

nvidia/active-speaker-detection
cURL
curl https://your-site.example/api/v1/chat/completions \
  -H "Authorization: Bearer $ROUTER_USER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nvidia/active-speaker-detection",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'