# Kling |  v3 | Turbo | Text to Video

Kling v3 Turbo Text-to-Video generates fast, cinematic clips straight from text prompts, with smooth motion and clear scenes. Made for quick ideation.

## API Information

- **Model Slug:** kling-v3-turbo-text-to-video
- **Branded URL:** https://www.eachlabs.ai/kling/kling-v3/kling-v3-turbo-text-to-video
- **Provider:** Kling
- **Category:** Text to Video
- **Output Type:** video
- **Status:** active
- **Base Cost:** $0.112–$0.14 per second, depending on resolution
- **Estimated Processing Time:** 200 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/kling-v3-turbo-text-to-video

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.112–$0.14 per second, depending on resolution
- **Pricing Details:** 1080p: $0.14
- **Pricing Details:** default: $0.112

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text prompt describing the desired video. Describe positive and negative elements directly in the text. |
| resolution | string | No | 720p | 720p, 1080p | Output video resolution. 720p is billed at a lower rate than 1080p. |
| aspect_ratio | string | No | 16:9 | 16:9, 9:16, 1:1 | Aspect ratio of the generated video frame. |
| duration | string | No | 5 | 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 | Video duration in seconds (3-15s). |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "kling-v3-turbo-text-to-video",
  "input": {
    "prompt": "A young woman with curly ginger hair plays joyfully with her fluffy Chow Chow dog on a sunlit green lawn. The Chow Chow has a thick lion-like mane and soft cream-colored fur. Framed as a medium shot that keeps both the woman and the dog fully in view, captured from a front three-quarter angle so the woman's smiling face stays clearly visible throughout. The dog wags its tail happily, trots over to the woman, sits down right beside her, and gently places one paw on her lap as she laughs and strokes its fluffy coat, her face lit and turned toward the camera. Soft natural daylight, a gentle breeze moving the grass and her hair, warm and candid atmosphere. Photorealistic, true-to-life colors, fine detail in the fur and skin, shallow depth of field with a softly blurred green park background, authentic real-footage look. The camera holds a steady framing on both of them, following their movements with smooth, natural motion while keeping the woman in frame."
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**Kling |  v3 | Turbo | Text to Video Overview**

Kling |  v3 | Turbo | Text to Video is a high-speed text-to-video generation model from Kling that converts natural language prompts into short, cinematic video clips. It is part of the Kling v3 model family, designed to deliver smooth motion, consistent character rendering, and strong adherence to complex scene descriptions. The primary differentiator of Kling |  v3 | Turbo | Text to Video is its balance of visual quality and fast turnaround, making it well-suited for iterative creative workflows where users need many variations quickly. Integrated on each::labs, this Kling text-to-video model gives creators, marketers, and developers a programmable way to generate story-driven video content directly from text, without traditional filming, animation, or editing pipelines.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.