Full Analysis (Gemini + Constellation)

import requests
url = "https://softskills-api.neurologyca.com/api/v1/full-analysis"
files = { "video": "open('interview_practice_2024-06-12.mp4', 'rb')" }
payload = {
    "sessionId": ,
    "transcript": ,
    "context_phrase": ,
    "mediapipeSamples": 
}
headers = {"Authorization": "Bearer <token>"}
response = requests.post(url, data=payload, files=files, headers=headers)
print(response.json())

{
  "sessionId": "session_20240612_0930",
  "gemini_analysis": {
    "overall_score": 87.5,
    "category_scores": {
      "likeability": 8.7,
      "authenticity": 9.1,
      "clarity": 8.5,
      "confidence": 8.9
    },
    "strengths": [
      "Clear articulation of key points",
      "Engaging eye contact",
      "Strong vocal variety"
    ],
    "areas_for_improvement": [
      "Reduce filler words",
      "Increase pacing consistency",
      "Enhance hand gestures for emphasis"
    ],
    "detailed_feedback": "The speaker demonstrated strong confidence and authenticity throughout the presentation. Clarity was generally good, though occasional filler words slightly detracted from the flow. Improving pacing and incorporating more deliberate hand gestures will enhance overall delivery.",
    "session_summary": "This session focused on practicing job interview responses with an emphasis on professional communication skills. The speaker showed notable strengths in engagement and vocal delivery.",
    "recommendation": "Continue practicing with a focus on pacing and reducing filler words. Consider recording practice sessions to self-evaluate hand gestures and eye contact.",
    "time_series_scores": [
      {
        "timestamp": "00:00:10",
        "likeability": 8.5,
        "authenticity": 9,
        "clarity": 8.3,
        "confidence": 8.7
      },
      {
        "timestamp": "00:00:20",
        "likeability": 8.8,
        "authenticity": 9.2,
        "clarity": 8.6,
        "confidence": 9
      },
      {
        "timestamp": "00:00:30",
        "likeability": 8.7,
        "authenticity": 9.1,
        "clarity": 8.7,
        "confidence": 8.9
      }
    ],
    "labeled_moments": [
      {
        "timestamp": "00:00:15",
        "label": "Strong Eye Contact",
        "text": "Maintained steady eye contact with the camera, enhancing engagement."
      },
      {
        "timestamp": "00:00:25",
        "label": "Filler Word Detected",
        "text": "Used 'um' twice in quick succession, slightly disrupting flow."
      }
    ]
  },
  "constellation_analysis": {
    "structured_data": {
      "triage": {},
      "emotion": {},
      "governance": {},
      "scientific_context": "Recent studies indicate that consistent eye contact and vocal variety significantly improve perceived confidence and authenticity in professional communication."
    },
    "interpretation": "The biometric data suggests the speaker maintained a high level of coherence and low cognitive effort, indicating comfort with the material. Minor frustration signals were detected during moments of filler word usage, suggesting areas for focus in future practice.",
    "metadata": {
      "model_version": "constellation-v2.3.1",
      "latency_ms": 450
    },
    "warnings": []
  },
  "constellation_kpis": {
    "coherence": 92,
    "cognitive_effort": 25,
    "rejection": 5,
    "frustration": 12,
    "stress_intensity": 18
  },
  "transcript": "Good morning everyone, thank you for joining this session. Today, I will be discussing the importance of effective communication in professional settings.",
  "videoUrl": "https://s3.amazonaws.com/neurologyca-videos/session_20240612_0930.mp4?X-Amz-Expires=3600&X-Amz-Signature=abcdef1234567890"
}

Upload a video and receive two analyses in parallel:

Gemini Video Analysis — scores (likeability, authenticity, clarity, confidence), strengths, areas for improvement, time-series scores, labeled moments, and detailed feedback.
Constellation Biometric Analysis — triage classification, emotion detection, governance (action flags, recommended actions), and a scientific interpretation narrative.

How it works

Thread 1 (Gemini): Video → Gemini AI → structured video analysis
Thread 2 (Constellation):
1. Transcript (user-provided or auto-generated via Deepgram)
2. 5 biometric KPIs derived from the transcript
3. KPIs + transcript → Constellation API → structured biometric analysis

Both threads run concurrently. If Constellation is not configured or fails, constellation_analysis will be null while gemini_analysis is still returned.

Upload a video and receive **two analyses in parallel**: 1. **Gemini Video Analysis** — scores (likeability, authenticity, clarity, confidence), strengths, areas for improvement, time-series scores, labeled moments, and detailed feedback. 2. **Constellation Biometric Analysis** — triage classification, emotion detection, governance (action flags, recommended actions), and a scientific interpretation narrative. ### How it works - **Thread 1 (Gemini):** Video → Gemini AI → structured video analysis - **Thread 2 (Constellation):** 1. Transcript (user-provided or auto-generated via Deepgram) 2. 5 biometric KPIs derived from the transcript 3. KPIs + transcript → Constellation API → structured biometric analysis Both threads run concurrently. If Constellation is not configured or fails, `constellation_analysis` will be null while `gemini_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.

sessionIdstringOptional

Optional session identifier

videofileRequired

Video file to analyze (MP4, WebM, MOV, AVI, MKV)

transcriptstringOptional

Optional session transcript. If empty or omitted, the API auto-generates one using Deepgram speech-to-text.

context_phrasestringOptionalDefaults to professional communication coaching session

Scenario description for Constellation contextual profiling (e.g. “job interview practice”, “sales pitch rehearsal”).

mediapipeSamplesstringOptional

Optional JSON array of MediaPipe face landmark samples

Response

Combined analysis result from Gemini and Constellation

sessionIdstring

The session identifier echoed back.

gemini_analysisobject

Full Gemini video analysis.

constellation_analysisobject or null

Constellation biometric analysis. Null if Constellation is not configured or the pipeline fails.

constellation_kpisobject or null

The 5 biometric KPIs derived from the transcript and sent to Constellation.

transcriptstring or null

Transcript used (user-provided or Deepgram-generated).

videoUrlstring or null

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