kling-v3 - Text to Video

Kuaishou’s Kling 3.0 t2v model. Generate videos from text prompts with camera control, multi-shot storyboarding, and sound generation.

Kling 3.0 t2v is a text-to-video generation model from Kuaishou’s Kling series, available through AnyFast API. Create videos from text descriptions with customizable camera movements, multi-shot storyboarding, and optional sound generation.

This page uses Kling’s Legacy API: POST /kling/v1/videos/text2video with the model_name field. It does not use the upgraded /text-to-video/kling-3.0 request structure.

Key capabilities

• Text-to-Video — Generate videos purely from text prompts
• Camera Control — Preset and custom camera movements (pan, tilt, zoom, roll)
• Multi-Shot — Create up to 6 storyboard shots with custom prompts and durations
• Sound Generation — Optionally generate synchronized sound or use up to 2 referenced voices
• Multiple Output Modes — std (720p), pro (1080p), and 4k

Quick example

cURL

curl https://www.anyfast.ai/kling/v1/videos/text2video \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "kling-3.0",
    "prompt": "A cat walking through a field of sunflowers at golden hour",
    "duration": "5",
    "mode": "std",
    "aspect_ratio": "16:9",
    "sound": "on"
  }'

Parameters

Parameter	Type	Required	Description
model_name	string	Yes	Must be kling-3.0
prompt	string	Conditional	Text prompt (max 2500 chars). Required for single-shot and intelligent storyboard generation
negative_prompt	string	No	Negative prompt (max 2500 chars)
mode	string	No	std (720p), pro (1080p), or 4k. Default: std
duration	string	No	3–15 seconds. Default: 5
aspect_ratio	string	No	16:9, 9:16, or 1:1. Default: 16:9
cfg_scale	float	No	Prompt relevance 0–1. Default: 0.5
multi_shot	boolean	No	Enable multi-shot storyboarding. Default: false
shot_type	string	Conditional	customize or intelligence. Required when multi_shot is true
multi_prompt	array	Conditional	1–6 storyboard shots. Required for customized storyboards; each prompt is at most 512 characters and shot durations must sum to duration
voice_list	array	No	Up to 2 voice IDs. Set sound to on and reference them as <<<voice_1>>>, <<<voice_2>>> in the prompt
sound	string	No	on or off. Default: off
camera_control	object	No	Camera movement control
watermark_info	object	No	Set enabled to generate an additional watermarked result

With multi_shot: true, use multi_prompt for shot_type: customize; use prompt for shot_type: intelligence. A voice list supports at most 2 entries, and referenced voices require sound: "on".

API Reference

View the interactive API playground for Kling 3.0 t2v.