Nara Lens/Docs

Quickstart

Get up and running with Nara Lens Active Speaker Detection.

Step 1: Get Your API Key

Sign up at naralens.com/auth/signup and create an API key from your dashboard.

Step 2: Submit a Video

Send a POST request with your video URL:

Bash
# Submit video for analysis
curl -X POST https://naralens.com/api/vad/analyze \
  -H "Authorization: Bearer $NARA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"video_url": "https://example.com/video.mp4"}'

# Response: {"task_id": "abc123", "status": "pending"}

Step 3: Poll for Results

Use the task_id from the response to check for results:

Bash
# Poll for results
curl https://naralens.com/api/vad/result/{task_id} \
  -H "Authorization: Bearer $NARA_API_KEY"

# Response when complete:
# {
#   "task_id": "abc123",
#   "status": "completed",
#   "video_duration": 30.5,
#   "frames": [{"frame": 0, "faces": [...], "active": true}]
# }

Step 4: Parse the Response

When processing is complete, you'll receive frame-by-frame analysis:

JSON
{
  "task_id": "abc123",
  "status": "completed",
  "video_duration": 30.5,
  "start_time": 1706000000.0,
  "end_time": 1706000045.0,
  "frames": [
    {
      "frame": 0,
      "faces": [
        {
          "bbox": [100, 50, 200, 180],
          "person_id": 1,
          "speaking_score": 0.95,
          "active": true
        }
      ]
    }
  ]
}

Billing

Credits are charged based on video duration: 1 credit = 1 second of video. For example, a 30-second video costs 30 credits.

Next Steps