> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mavera.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Sound/Music Impact Analysis

> Compare the same visual with different audio tracks to measure which audio treatment maximizes emotional response on TikTok.

### Scenario

TikTok is an audio-first platform — the same visual with different audio can produce wildly different engagement. This job takes video ad variants that share the same visual but use different audio tracks (trending sound vs. original music vs. voiceover-only), runs Video Analysis on each, and compares emotional intensity, mood congruence, and pacing alignment. The result tells you exactly which audio treatment maximizes emotional response for your visual content.

### Architecture

```mermaid theme={"dark"}
flowchart LR
    A["Upload same-visual/different-audio variants"] --> B["Mavera POST /video-analysis per variant"]
    B --> C["Compare emotional intensity + mood + pacing"]
    C --> D["Audio impact report"]
```

### Code

<CodeGroup>
  ```python Python theme={"dark"}
  import os, requests, time

  MV = os.environ["MAVERA_API_KEY"]
  MV_BASE = "https://app.mavera.io/api/v1"
  MV_H = {"Authorization": f"Bearer {MV}", "Content-Type": "application/json"}

  VIDEO_VARIANTS = [
      {"path": "ads/product_demo_trending_sound.mp4", "label": "Trending Sound", "audio": "Espresso remix — high energy, beat drops at cuts"},
      {"path": "ads/product_demo_original_music.mp4", "label": "Original Music", "audio": "Custom lo-fi track — chill, ambient, brand-composed"},
      {"path": "ads/product_demo_voiceover.mp4", "label": "Voiceover Only", "audio": "Founder narration — direct, educational, no background music"},
      {"path": "ads/product_demo_asmr.mp4", "label": "ASMR / Product Sounds", "audio": "Product interaction sounds — tapping, pouring, unboxing"},
  ]

  # 1. Upload all variants and run analysis
  analyses = []
  for variant in VIDEO_VARIANTS:
      upload = requests.post(f"{MV_BASE}/assets",
          headers={"Authorization": f"Bearer {MV}"},
          files={"file": (variant["label"] + ".mp4", open(variant["path"], "rb"), "video/mp4")},
      ).json()

      analysis = requests.post(f"{MV_BASE}/video-analysis", headers=MV_H, json={
          "asset_id": upload["id"],
          "analysis_types": ["emotional_arc", "mood_congruence", "pacing", "hook_score", "audio_impact"],
          "metadata": {"label": variant["label"], "audio_description": variant["audio"]},
      }).json()

      analyses.append({"id": analysis["id"], "label": variant["label"], "audio": variant["audio"]})
      time.sleep(0.5)

  # 2. Poll all analyses
  results = []
  for a in analyses:
      for _ in range(30):
          time.sleep(3)
          status = requests.get(f"{MV_BASE}/video-analysis/{a['id']}", headers=MV_H).json()
          if status.get("status") == "completed":
              break
      r = status.get("results", {})
      results.append({
          "label": a["label"],
          "audio": a["audio"],
          "emotional_intensity": r.get("emotional_arc", {}).get("intensity_avg", 0),
          "peak_emotion": r.get("emotional_arc", {}).get("peak_emotion", "N/A"),
          "peak_timestamp": r.get("emotional_arc", {}).get("peak_timestamp", 0),
          "mood_congruence": r.get("mood_congruence", {}).get("score", 0),
          "pacing_score": r.get("pacing", {}).get("score", 0),
          "hook_score": r.get("hook_score", {}).get("score", 0),
          "audio_energy": r.get("audio_impact", {}).get("energy", 0),
      })

  # 3. Comparative report
  results.sort(key=lambda x: -x["emotional_intensity"])

  print("SOUND/MUSIC IMPACT ANALYSIS — Same Visual, Different Audio")
  print("=" * 70)
  print(f"{'Variant':<22} {'Emotion':<10} {'Mood Fit':<10} {'Pacing':<10} {'Hook':<8} {'Audio E'}")
  print("-" * 70)
  for r in results:
      print(f"{r['label']:<22} {r['emotional_intensity']:.1f}/10   {r['mood_congruence']:.1f}/10   {r['pacing_score']:.1f}/10   {r['hook_score']}/100  {r['audio_energy']:.1f}")

  # 4. Recommendation
  best = results[0]
  worst = results[-1]
  delta = best["emotional_intensity"] - worst["emotional_intensity"]
  print(f"\nWINNER: {best['label']}")
  print(f"  Emotional intensity: {best['emotional_intensity']:.1f}/10 (peak: {best['peak_emotion']} at {best['peak_timestamp']}s)")
  print(f"  Mood congruence: {best['mood_congruence']:.1f}/10")
  print(f"  vs worst ({worst['label']}): +{delta:.1f} emotional intensity")
  print(f"\nRECOMMENDATION: Use '{best['label']}' audio treatment for this visual.")
  if best["mood_congruence"] < 6:
      print(f"  ⚠ Mood congruence is low ({best['mood_congruence']:.1f}). Audio energy may not match visual tone — test with audience.")
  ```

  ```javascript JavaScript theme={"dark"}
  const MV = process.env.MAVERA_API_KEY;
  const MV_BASE = "https://app.mavera.io/api/v1";
  const MV_H = { Authorization: `Bearer ${MV}`, "Content-Type": "application/json" };
  const fs = await import("fs");

  const VIDEO_VARIANTS = [
    { path: "ads/product_demo_trending_sound.mp4", label: "Trending Sound", audio: "Espresso remix — high energy" },
    { path: "ads/product_demo_original_music.mp4", label: "Original Music", audio: "Custom lo-fi — chill, ambient" },
    { path: "ads/product_demo_voiceover.mp4", label: "Voiceover Only", audio: "Founder narration — educational" },
    { path: "ads/product_demo_asmr.mp4", label: "ASMR / Product Sounds", audio: "Product sounds — tapping, unboxing" },
  ];

  // 1. Upload and analyze
  const analyses = [];
  for (const variant of VIDEO_VARIANTS) {
    const formData = new FormData();
    const fileBuffer = fs.readFileSync(variant.path);
    formData.append("file", new Blob([fileBuffer], { type: "video/mp4" }), `${variant.label}.mp4`);

    const upload = await fetch(`${MV_BASE}/assets`, {
      method: "POST", headers: { Authorization: `Bearer ${MV}` }, body: formData,
    }).then(r => r.json());

    const analysis = await fetch(`${MV_BASE}/video-analysis`, {
      method: "POST", headers: MV_H,
      body: JSON.stringify({
        asset_id: upload.id,
        analysis_types: ["emotional_arc", "mood_congruence", "pacing", "hook_score", "audio_impact"],
        metadata: { label: variant.label, audio_description: variant.audio },
      }),
    }).then(r => r.json());

    analyses.push({ id: analysis.id, label: variant.label, audio: variant.audio });
    await new Promise(r => setTimeout(r, 500));
  }

  // 2. Poll
  const results = [];
  for (const a of analyses) {
    let status;
    for (let i = 0; i < 30; i++) {
      await new Promise(r => setTimeout(r, 3000));
      status = await fetch(`${MV_BASE}/video-analysis/${a.id}`, { headers: MV_H }).then(r => r.json());
      if (status.status === "completed") break;
    }
    const r = status.results || {};
    results.push({
      label: a.label, audio: a.audio,
      emotional_intensity: r.emotional_arc?.intensity_avg || 0,
      peak_emotion: r.emotional_arc?.peak_emotion || "N/A",
      peak_timestamp: r.emotional_arc?.peak_timestamp || 0,
      mood_congruence: r.mood_congruence?.score || 0,
      pacing_score: r.pacing?.score || 0,
      hook_score: r.hook_score?.score || 0,
      audio_energy: r.audio_impact?.energy || 0,
    });
  }

  // 3. Report
  results.sort((a, b) => b.emotional_intensity - a.emotional_intensity);
  console.log("SOUND/MUSIC IMPACT ANALYSIS — Same Visual, Different Audio");
  console.log("=".repeat(70));
  console.log("Variant               Emotion   Mood Fit  Pacing    Hook    Audio E");
  console.log("-".repeat(70));
  for (const r of results) {
    console.log(`${r.label.padEnd(22)} ${r.emotional_intensity.toFixed(1)}/10   ${r.mood_congruence.toFixed(1)}/10   ${r.pacing_score.toFixed(1)}/10   ${r.hook_score}/100  ${r.audio_energy.toFixed(1)}`);
  }

  const best = results[0];
  const worst = results[results.length - 1];
  console.log(`\nWINNER: ${best.label}`);
  console.log(`  Emotional intensity: ${best.emotional_intensity.toFixed(1)}/10 (peak: ${best.peak_emotion} at ${best.peak_timestamp}s)`);
  console.log(`  vs worst (${worst.label}): +${(best.emotional_intensity - worst.emotional_intensity).toFixed(1)} emotional intensity`);
  ```
</CodeGroup>

### Example Output

```text theme={"dark"}
SOUND/MUSIC IMPACT ANALYSIS — Same Visual, Different Audio
======================================================================
Variant               Emotion   Mood Fit  Pacing    Hook    Audio E
----------------------------------------------------------------------
Trending Sound        8.4/10    7.2/10    9.1/10    89/100  9.0
ASMR / Product Sounds 7.1/10    8.8/10    6.5/10    72/100  3.2
Voiceover Only        6.3/10    7.9/10    7.0/10    68/100  2.1
Original Music        5.8/10    6.1/10    5.4/10    55/100  5.5

WINNER: Trending Sound
  Emotional intensity: 8.4/10 (peak: excitement at 3.8s)
  Mood congruence: 7.2/10
  vs worst (Original Music): +2.6 emotional intensity

RECOMMENDATION: Use 'Trending Sound' audio treatment for this visual.

KEY INSIGHT: Trending Sound wins on emotion (+2.6 over Original Music)
and pacing (+3.7) because beat drops align with visual cuts. However,
ASMR scores highest on mood congruence (8.8) — the product sounds
feel most authentic to the visual. Consider ASMR for organic posts
and Trending Sound for paid amplification.
```

### Error Handling

<AccordionGroup>
  <Accordion title="Identical visual validation">Ensure all variants share the exact same visual edit. If visuals differ even slightly (different color grades, trimmed frames), the audio comparison is contaminated. Use a single exported visual with separate audio mixes.</Accordion>
  <Accordion title="Audio analysis availability">The `audio_impact` analysis type may require a specific Mavera plan tier. If unavailable, use `emotional_arc` + `pacing` as proxies for audio effect.</Accordion>
  <Accordion title="File size limits">TikTok ads can be up to 500MB. Mavera asset uploads may have lower limits. Compress to 720p/1080p before uploading. H.264 codec recommended.</Accordion>
</AccordionGroup>

***

<CardGroup cols={2}>
  <Card title="All TikTok jobs" icon="tiktok" href="/integrations/tiktok" />

  <Card title="Video Analysis" icon="video" href="/features/video-analysis" />
</CardGroup>