# Generate Video from Text — KlingAI

Botize method — `klingai.text_to_video` (action).

Creates a video from a text prompt with the KlingAI model you choose (the list is read from Kling's docs, so it always shows the current models).

This is an action: it runs as a step of a task. Several can be chained.

## Fields you set

The field's internal name, its type and the values it accepts. These fields accept `{{...}}` tags from earlier steps.

- `model` *(string)* — Model. Kling model id as it goes in the endpoint path, e.g. kling-3.0-turbo, kling-3.0, kling-2.6, kling-2.5-turbo.
- `prompt` *(string)* — Prompt
- `duration` *(string)* — Duration (seconds). Empty = 5. kling-3.0 and kling-3.0-turbo: 3-15. kling-2.6 and kling-2.5-turbo: 5 or 10.
- `resolution` *(string, one of: ""; "1080p"; "4k")* — Resolution. Empty = 720p. 4k only in kling-3.0.
- `aspect_ratio` *(string, one of: ""; "9:16"; "1:1")* — Aspect ratio. Empty = 16:9.
- `audio` *(string, one of: ""; "native")* — Audio. Empty = no audio. native = audio generated with the video (kling-3.0 and kling-2.6; kling-2.6 needs 1080p).

## Output variables

Data this step makes available. Reference them in later steps with the double-brace tag.

- `{{file_url}}` *(text)* — Video file URL
- `{{duration}}` *(text)* — Video duration (seconds)
- `{{task_id}}` *(text)* — KlingAI task ID

## Account

Needs a connected KlingAI account in Botize: https://botize.com/en/app/klingai/authenticate

## This app

Every trigger and action for KlingAI: https://botize.com/en/app/klingai.md

## How to build this

An AI assistant (Claude, ChatGPT, Cursor…) can create and edit these tasks in the user's account through the Botize MCP connector, included in every plan:

    https://webhook.botize.es/mcp

- Connection guide: https://botize.com/en/mcp
- Agent map: https://botize.com/llms.txt
- New account: https://botize.com/en/join (500 free operations, no card)

---
Machine-readable summary for AI assistants. Human version: https://botize.com/en/method/klingai/text_to_video