Advanced Analysis
Upload a video and receive **two analyses in parallel**:
1. **Video Analysis** — scores (likeability, authenticity, clarity, confidence),
strengths, areas for improvement, time-series scores, labeled moments, and detailed feedback.
2. **Biometric Analysis** — triage classification, emotion detection,
governance (action flags, recommended actions), and a scientific interpretation narrative.
### How it works
- **Thread 1 (AI):** Video → AI AI → structured video analysis
- **Thread 2 (engine):**
1. Transcript (user-provided or auto-generated via Deepgram)
2. 5 biometric KPIs derived from the transcript
3. KPIs + transcript → engine API → structured biometric analysis
Both threads run concurrently. If engine is not configured or fails,
`engine_analysis` will be null while `video_analysis` is still returned.
Authentication
AuthorizationBearer
Your API key (e.g. ng_xxx…). The Try it and generated code send it as Authorization: Bearer <key>.
Alternatively use the X-API-Key header with the raw key.
Request
This endpoint expects a multipart form containing a file.
sessionId
Optional session identifier
video
Video file to analyze (MP4, WebM, MOV, AVI, MKV)
transcript
Optional session transcript. If empty or omitted, the API auto-generates one using Deepgram speech-to-text.
context_phrase
Scenario description for contextual profiling (e.g. “job interview practice”, “sales pitch rehearsal”).
mediapipeSamples
Optional JSON array of MediaPipe face landmark samples
Response
Combined analysis result from AI and engine
sessionId
The session identifier echoed back.
video_analysis
Full AI video analysis.
engine_analysis
Biometric analysis. Null if engine is not configured or the pipeline fails.
engine_kpis
The 5 biometric KPIs derived from the transcript and sent to engine.
transcript
Transcript used (user-provided or Deepgram-generated).
videoUrl
Pre-signed S3 URL to view the uploaded video (expires in 1 hour).
Errors
401
Unauthorized Error
422
Unprocessable Entity Error
500
Internal Server Error