Kling v3.0 Text-to-Video

Kling v3.0 Text-to-Video is Kuaishou's next-generation AI video model. Powered by the native Omni architecture, it accurately parses complex prompt text to generate up to 4K cinematic-grade videos up to 15 seconds long. It natively supports integrated audio-video generation (ambient audio, music, and multilingual lip-sync) alongside exceptional visual realism, multi-shot coherence, and complex physical simulation—ideal for commercial advertising, film VFX, and content creation.

Kling v3.0 Text-to-Video

Base URL

https://api.icreat.ai

Authentication

All API requests must be authenticated with an API Key. You can obtain an API Key from the console.

export ICREAT_API_KEY="your-api-key-here"

HTTP Request Headers

import os

API_KEY = os.environ.get("ICREAT_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer " + API_KEY,
}

Protect your API Key

Never expose your API Key in client-side code or public repositories. Use environment variables or a backend proxy.

Code Examples

Image and video generation uses a three-step async flow: submit to get task_id, poll status, then fetch results when status is SUCCEEDED.

1. Submit Task

Send a generation request to the submit endpoint.

POST/v1/task/submit/kwaivgi/kling-v3-0/text-to-video

curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/submit/kwaivgi/kling-v3/text-to-video" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Example multiline\ntext",
    "mode": "std",
    "duration": 4
  }'

2. Poll Status

Poll with task_id. Response contains only status.

POST/v1/task/query-status

curl --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/query-status" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "task_id": "task-xxx"
  }'

3. Get Result

Fetch output when the task succeeds.

POST/v1/task/get-result

curl --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/get-result" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "task_id": "task-xxx"
  }'

Input Schema

Submit Task — Input

Total: 3 Required: 3 Optional: 0

promptstringrequired

The prompt used to generate the video. Chinese prompts must not exceed 2,000 characters, and English prompts must not exceed 2,000 words.

modestringrequired

Output resolution mode. Supported values: std, pro, and 4k.

durationintegerrequired

Video duration in seconds. Accepted range: 4–15.

Poll Status — Input

Total: 1 Required: 1 Optional: 0

task_idstringrequired

Task ID from the submit endpoint.

Get Result — Input

Total: 1 Required: 1 Optional: 0

task_idstringrequired

Task ID from the submit endpoint.

Output Schema

Submit Task — Output

Total: 1

task_idstring

Async task identifier.

Poll Status — Output

Total: 1

statusstring

Current task status. Fetch results when SUCCEEDED.

Get Result — Output

Top-level array of resource objects.

Total: 3

typestring

Resource type; Video for this model.

urlstring

Preview/access URL.

download_urlstring

Download URL.

LLM Prompt

The Markdown below is an LLM-friendly prompt you can paste into AI assistants (e.g. Cursor, ChatGPT) to help them understand this model's API, call flow, and key parameters. Use Copy for AI or copy from the code block below.

# kwaivgi/kling-v3-0/text-to-video

> Kling v3.0 Text-to-Video is Kuaishou's next-generation AI video model.

## Overview

Use the iCreat three-step async task API: submit a generation request, poll status, then fetch the video URL on success.

## API Info

- **Base URL**：`https://api.icreat.ai`
- **Submit endpoint (POST)**：`/v1/task/submit/kwaivgi/kling-v3-0/text-to-video`
- **Poll endpoint (POST)**：`/v1/task/query-status`
- **Get result endpoint (POST)**：`/v1/task/get-result`
- **Model ID**：`kwaivgi/kling-v3-0/text-to-video`
- **Auth**：`Authorization: Bearer ${ICREAT_API_KEY}`

## Call Flow

1. **Submit**: POST submit path with body per Input Notes; response `{ "task_id": "..." }`
2. **Poll**: POST `/v1/task/query-status` with `{ "task_id": "..." }`; response contains **only** `{ "status": "SUBMITTED|SUCCEEDED|FAILED" }`
3. **Get result**: when `status` is `SUCCEEDED`, POST `/v1/task/get-result`; top-level array; read `url` or `download_url` when `type` is `Video`

### Input Notes

- Request body uses top-level flat fields
- Required: `prompt`, `mode`, `duration`
- `prompt` (required): The prompt used to generate the video. Chinese prompts must not exceed 2,000 characters, and English prompts must not exceed 2,000 words.
- `mode` (required): Output resolution mode. Supported values: `std`, `pro`, and `4k`.
- `duration` (required): Video duration in seconds. Accepted range: `4`–`15`.

### Output Notes

- Poll: read `status` only
- Result: top-level `[{ "type": "Video", "url": "...", "download_url": "..." }]`

## Notes

- Use the same `task_id` across all three steps; do not skip polling
- `FAILED` is terminal — check request parameters or reference media