YouTube Clipper API

When to use it

• Podcasters with hour-long episodes who want 5-10 shorts per episode.
• YouTubers who want to auto-distribute clips to TikTok and Reels without manual editing.
• Course creators with lecture footage looking to extract teasers.
• Companies with conference talks who want to surface highlights.

For raw video → social post workflows, pair this with Multi-Platform Post.

Endpoint

POST /api/v1/clipper/youtube

Quickstart

curl -X POST https://api.reelsbuilder.ai/api/v1/clipper/youtube \
  -H "Authorization: Bearer $REELSBUILDER_API_KEY" \
  -H "Idempotency-Key: $(uuidgen)" \
  -H "Content-Type: application/json" \
  -d '{
    "youtube_url": "https://youtube.com/watch?v=abc123",
    "clip_count": 5,
    "clip_duration_target_sec": 45,
    "captions": true,
    "face_tracking": true,
    "webhook_url": "https://your-app.example.com/webhooks/clips"
  }'

Initial response

{
  "success": true,
  "data": {
    "job_id": "cjob_01HKZ...",
    "status": "queued",
    "estimated_completion_sec": 240,
    "source": {
      "youtube_url": "https://youtube.com/watch?v=abc123",
      "duration_sec": 3420,
      "title": "How we ship 10x faster than competitors"
    }
  },
  "meta": { "request_id": "req_...", "credits_used": 50, "credits_remaining": 950 }
}

Completion webhook

POST https://your-app.example.com/webhooks/clips
X-RB-Event-Type: clips.completed

{
  "event_id": "evt_...",
  "event_type": "clips.completed",
  "data": {
    "job_id": "cjob_01HKZ...",
    "status": "completed",
    "clips": [
      {
        "clip_id": "clp_01HKZ...",
        "title": "The 3-day shipping rule",
        "url": "https://cdn.reelsbuilder.ai/c/clp_.../clip.mp4",
        "thumbnail_url": "https://cdn.reelsbuilder.ai/c/clp_.../thumb.jpg",
        "source_start_sec": 412,
        "source_end_sec": 458,
        "duration_sec": 46,
        "viral_score": 0.91,
        "transcript": "So the way we ship 10x faster is...",
        "keywords": ["shipping velocity", "engineering culture"]
      }
    ],
    "credits_used": 50,
    "credits_refunded": 0
  }
}

Parameters

How viral score works

Every candidate clip is scored 0.0–1.0 by a model that looks at:

• Hook strength — does the opening 3 seconds grab attention?
• Self-contained narrative — does the clip work without context from the rest of the video?
• Engagement signals — laughs, gasps, "wait, what?" reactions, tonal shifts
• Quotability — punchy lines that could become captions

Default filter is 0.6 (decent). For top-quality only, use 0.85.

Examples

TypeScript

const r = await fetch("https://api.reelsbuilder.ai/api/v1/clipper/youtube", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.REELSBUILDER_API_KEY}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify({
    youtube_url: "https://youtube.com/watch?v=abc123",
    clip_count: 5,
    min_viral_score: 0.85,
    brand_id: process.env.BRAND_ID,
    webhook_url: "https://your-app.example.com/webhooks/clips",
  }),
});
const { data: job } = await r.json();
console.log(`Job ${job.job_id} — ${job.source.title} (~${job.estimated_completion_sec}s)`);

Python

import os, uuid, requests

r = requests.post(
    "https://api.reelsbuilder.ai/api/v1/clipper/youtube",
    headers={
        "Authorization": f"Bearer {os.environ['REELSBUILDER_API_KEY']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "youtube_url": "https://youtube.com/watch?v=abc123",
        "clip_count": 5,
        "min_viral_score": 0.85,
        "brand_id": os.environ.get("BRAND_ID"),
        "webhook_url": "https://your-app.example.com/webhooks/clips",
    },
)
job = r.json()["data"]
print(f"Job {job['job_id']} - {job['source']['title']} ({job['estimated_completion_sec']}s)")

Chained with multi-platform posting

Once clips are ready, fan-out post all of them in parallel:

// In your webhook handler
for (const clip of payload.data.clips) {
  await fetch("https://api.reelsbuilder.ai/api/v1/post", {
    method: "POST",
    headers: { ...auth, "Idempotency-Key": clip.clip_id },
    body: JSON.stringify({
      video_url: clip.url,
      caption: clip.title,
      platforms: ["tiktok", "instagram", "youtube_shorts"],
    }),
  });
}

Pricing

• 10 credits per clip returned. The base cost in the initial response is your clip_count × 10.
• No charge for clips filtered out by min_viral_score. If you ask for 10 and only 7 pass the threshold, you're charged 70 credits and refunded 30.
• Source video processing is free. No per-minute fee for the input.

Source video limits

• Max source duration: 4 hours
• Min source duration: 60 seconds (anything shorter is rejected)
• Languages supported: 99 via ElevenLabs Scribe v2 STT
• Private/unlisted YouTube videos require youtube_oauth_token with read scope

See also

• Transcribe + Captions API — caption an arbitrary video URL
• Multi-Platform Post API — distribute the clips
• Webhooks — receive completion event