# Skill: effect/keyword-cta — "תגיבו ״מילה״" (Comment-keyword CTA)

The speaker blurs and dims, and a “comment KEYWORD” sticker slams in on a flash with a deep boom.
הדובר מיטשטש ומחשיך, ומדבקת ״תגיבו מילה״ נוחתת בהבזק עם בום עמוק.

Category: Overlays & graphics · שכבות וגרפיקה · a real preview: https://media.gpt.org.il/lookbook/effects/keyword-cta.mp4?v=mv19exzc
Price: **60 credits per finished minute**: the render itself — 1 credit per second of 1080p output. Combined with captions, a hook or other effects: still one render, nothing more for combining.

Base URL: `https://apihub.co.il` · Auth: `Authorization: Bearer <API key>` · Docs: `/docs` (group "Video Effects")
Send `X-Tag: <job name>` on every call of one video; `GET /v1/usage?tag=<job name>` returns what it cost.
**Files are kept 24 hours** — download the finished video.

---

## 1. On its own — one call

```jsonc
POST /v1/effects/keyword-cta             // x-wait-ms: 110000
{
  "video_url": "https://media.gpt.org.il/samples/sample-he.mp4",
  "start": 0.2,
  "duration": 4,
  "params": {
    "keyword": "נוסחה"
  }
}
```

A normal render: `status: processing` → poll `GET /v1/executions/{id}` until `completed`, then read `output.url`.
Leave out `video_url` and the effect is drawn on a plain black canvas (9:16 unless `output.aspect_ratio` says otherwise).

When it plays: a stretch: `start` + `duration` (seconds of the finished video), or `at` (a word id) + `duration`, or `during` { from, to } (word ids).

## 2. With captions, a hook and other effects — the same render

```jsonc
POST /v1/studio/edit               // x-wait-ms: 110000
{
  "video_url": "<the video>",
  "language_code": "he",
  "captions": {
    "style": "classic"
  },
  "effects": [
    {
      "id": "keyword-cta",
      "params": {
        "keyword": "נוסחה"
      },
      "start": 0.2,
      "duration": 4
    }
  ],
  "audio": {
    "normalize": true
  },
  "output": {
    "aspect_ratio": "9:16",
    "resolution": "1080",
    "fit": "crop",
    "quality": "high"
  }
}
```

`effects` is a list: add more entries for more effects. The engine applies them by pipeline stage (cuts and time →
camera → grade and looks → overlays → text and captions → sound), never by their order in the list. An edit has one
`transition`, one `color` grade, one `music` bed, one `speed` and one caption style: two effects that set the same
one are refused with a message that names them.

## 3. Params

| param | default | range / options | what it does |
|---|---|---|---|
| `keyword` | **required** | string | The word to comment |
| `prompt` | `"תגיבו"` | string | The words before it |
| `sub` | `""` | string | A smaller line under the sticker ("" = none) |
| `accent` | `"#DE124B"` | string | The keyword's colour |
| `size` | `6` | 3–14 | Sticker text size, % of the frame height |
| `y` | `30` | 5–90 | Height of the sticker, % from the top |
| `blur` | `18` | 0–40 | Blur of the speaker behind, px at 1080 wide |
| `dim` | `0.45` | 0–0.9 | How dark the speaker gets |
| `sound` | `"boom"` | `boom` · `hit` · `none` | The sound as the sticker lands |

GET `/v1/effects/keyword-cta` returns the same as JSON (with the full body schema). Every field has a default; numbers
outside their range are refused with the field's name.