Kling 3.0 Std

Standard QualityNative AudioMotion Transfer

Kuaishou’s Kling Video 3.0 Standard combines text-to-video, image animation, and character motion transfer on APIXO. It extends generated clips to 15 seconds, supports optional native audio, and adds shot-level prompting for stronger narrative control, while motion-control pairs one character image with one reference performance video.

APIXO Modes

Generate / Animate / Transfer

Silent Price

$0.084/secText and image modes without generated sound

Generated Sound Price

$0.13/secText and image modes with generated audio

Generation Length

3–15 seconds

Released

Feb 5, 2026

Loading workspace...

Kling 3.0 Std Model API Rate Structure

Text-to-video / image-to-video

Billing basis

Sound disabled, selected duration

APIXO price

$0.084 / second

Text-to-video / image-to-video

Billing basis

Sound enabled, selected duration

APIXO price

$0.13 / second

Motion-control

Billing basis

Detected reference-video duration

APIXO price

$0.13 / second

Workflow	Billing basis	APIXO price
Text-to-video / image-to-video	Sound disabled, selected duration	$0.084 / second
Text-to-video / image-to-video	Sound enabled, selected duration	$0.13 / second
Motion-control	Detected reference-video duration	$0.13 / second

Checking API access...

Integrate with AI

Copy a prompt for your AI assistant to install APIXO MCP, read the live schema, and wire this model into your app.

Endpoints

Create task

POSThttps://api.apixo.ai/api/v1/generateTask/kling-3-0-std

Poll status

GEThttps://api.apixo.ai/api/v1/statusTask/kling-3-0-std?taskId={taskId}

Request body

request_type

async

Use callback with callback_url for webhooks.

input

object

Mode, prompt, references, size, duration, and audio settings.

request_typerequired

Typeselect

Use async to poll statusTask, or callback to receive a webhook when the result is ready.async · callback

callback_urlconditional

Typetext

Public HTTPS URL for callback delivery.Only in request_type=callback

moderequired

Typeselect

Choose text-to-video, image-to-video, or motion-control.text-to-video · image-to-video · motion-control

promptoptional

Typestring

Required for text-to-video and image-to-video; optional for motion-control.

durationconditional

Typeslider

Used for text-to-video and image-to-video. Motion-control detects duration from the reference video.Only in mode=text-to-video | image-to-video

soundoptional

Typeboolean

Generate audio for text/image modes, or retain original audio for motion-control.

aspect_ratioconditional

Typeselect

Text-to-video only.1:1 · 9:16 · 16:9Only in mode=text-to-video

character_orientationconditional

Typeselect

Motion-control only. Choose whether orientation follows the character image or motion video.image · videoOnly in mode=motion-control

negative_promptoptional

Typestring

Optional negative prompt. If provided, it must be non-empty.

cfg_scaleoptional

Typeslider

Guidance scale for text-to-video and image-to-video.

Parameter	Type	Required	Description
`request_type`	select	required	Use async to poll statusTask, or callback to receive a webhook when the result is ready.async · callback
`callback_url`	text	conditional	Public HTTPS URL for callback delivery.Only in request_type=callback
`mode`	select	required	Choose text-to-video, image-to-video, or motion-control.text-to-video · image-to-video · motion-control
`prompt`	string	optional	Required for text-to-video and image-to-video; optional for motion-control.
`duration`	slider	conditional	Used for text-to-video and image-to-video. Motion-control detects duration from the reference video.Only in mode=text-to-video \| image-to-video
`sound`	boolean	optional	Generate audio for text/image modes, or retain original audio for motion-control.
`aspect_ratio`	select	conditional	Text-to-video only.1:1 · 9:16 · 16:9Only in mode=text-to-video
`character_orientation`	select	conditional	Motion-control only. Choose whether orientation follows the character image or motion video.image · videoOnly in mode=motion-control
`negative_prompt`	string	optional	Optional negative prompt. If provided, it must be non-empty.
`cfg_scale`	slider	optional	Guidance scale for text-to-video and image-to-video.

File parameters (URL arrays)

image_urls[mode=image-to-video | motion-control]Image-to-video supports 1-2 images; motion-control requires exactly one character image.Only in mode=image-to-video | motion-control

video_urls[mode=motion-control]Upload one public MP4, MOV, or M4V video. Videos over 30 seconds are rejected.Only in mode=motion-control

Example (cURL)

curl -X POST "https://api.apixo.ai/api/v1/generateTask/kling-3-0-std" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "request_type": "async",
    "input": {
      "mode": "text-to-video",
      "prompt": "a cinematic city skyline at sunset, slow camera push-in",
      "negative_prompt": "blur, low quality",
      "duration": 5,
      "sound": true,
      "aspect_ratio": "16:9",
      "cfg_scale": 0.5
    }
  }'

Full API documentation

Capabilities

Greater control over narrative and continuity

Extended Scene Duration

Kling Video 3.0 extends native generation to 15 seconds, giving actions, dialogue, camera changes, and scene development more room than Kling Video 2.6’s ten-second maximum.

Multi-Shot Storytelling

Kuaishou designed Video 3.0 to interpret multi-scene and multi-shot instructions, including changing camera angles, shot-reverse-shot dialogue, cross-cutting, and voice-over. APIXO exposes optional timed prompt segments for text- and image-led generation.

Stronger Element Consistency

Improved consistency helps characters, objects, environments, and branded elements remain more coherent across frames. Complex movement and longer sequences can still introduce visual drift and require review.

Multilingual Native Audio

Upstream Video 3.0 supports generated speech in English, Chinese, Japanese, Korean, and Spanish, alongside English accents and Chinese dialects. APIXO exposes generated audio through the sound control for text- and image-led modes.

Better Text Preservation

Kuaishou reports improved retention and generation of visible text such as signage, captions, logos, and branded clothing. Exact spelling and placement should still be checked before commercial use.

Photorealistic Performance

Video 3.0 improves photorealistic output for expressive characters and dynamic performances. Detailed prompts can coordinate subject behavior, camera direction, scene progression, and sound within one generated sequence.

APIXO Workflow Groups

Generate a new scene or transfer existing motion

Text and Image Generation

Create from a prompt or animate one to two images for 3–15 seconds. Choose generated sound or silent output, and optionally divide the clip into timed prompt segments for shot-level direction.

New Video

Character Motion Control

Combine exactly one character image with one reference motion video. Choose whether orientation follows the image or video; duration comes from the reference clip, and the sound setting determines whether its original audio is retained.

Motion Transfer

Production Specifications

Kling 3.0 Standard on APIXO

Workflow-specific controls for generation and motion transfer.

1:1 / 9:16 / 16:9

Text-to-Video Ratios

1–2 images

Image-to-Video

1 image + 1 video

Motion Control

Up to 30 seconds

Motion Reference

JPG / JPEG / PNG

Image Formats

1 MP4 URL

APIXO Output

Production Uses

Develop stories, performances, and branded motion

Narrative Content

Multi-Shot Scene Prototypes

Structure a longer generated clip with timed prompt segments for establishing shots, close-ups, reactions, and transitions. Use the result to test narrative rhythm, camera changes, dialogue flow, and scene logic before production.

Character Animation

Reference Performance Transfer

Apply movement from a short reference video to a character image for performance studies, choreography tests, or stylized animation. Select orientation according to whether body direction should follow the source image or motion footage.

Marketing

Branded Audio-Visual Campaigns

Create product showcases, narrated advertisements, and short social campaigns with optional native speech, music, ambience, and effects. Review product geometry, visible text, logos, vocal wording, and synchronization before publishing.

Dialogue

Multilingual Conversation Concepts

Prototype conversations, interviews, and cross-language scenes using Kling Video 3.0’s native voice capabilities. Clearly specify each speaker, language, order, tone, and action, then verify attribution, pronunciation, lip movement, and continuity.

Integration Notes

Apply the correct sound and duration rules

APIXO constraints

Text-to-video and image-to-video accept 3–15-second duration; motion-control ignores that field.

Image-to-video accepts one starting image and an optional second image that can guide the ending frame.

Motion-control requires exactly one character image and one public reference video no longer than 30 seconds.

Aspect-ratio selection applies only to text-to-video through APIXO.

APIXO exposes no separate uploaded-audio, video-extension, video-editing, or arbitrary multi-reference mode here.

Production integrations can retrieve asynchronous results through polling or a public HTTPS callback.

Kling 3.0 Standard questions

Yes. APIXO labels and prices this route as Kling 3.0 Standard. It is separate from Kling 3.0 Turbo and Video 3.0 Omni, so their speed, reference features, editing controls, and pricing should not be applied here.

Text-to-video and image-to-video cost $0.084 per generated second with sound disabled or $0.13 per second with sound enabled. Their billable duration is the selected value from 3 through 15 seconds.

APIXO charges motion-control at $0.13 per detected reference-video second, with a minimum of three billable seconds. The submitted duration field is ignored, and reference videos longer than 30 seconds are rejected.

For text-to-video and image-to-video, sound: true requests model-generated audio and false produces silent output. In motion-control, the same field determines whether the reference video’s original audio is retained rather than requesting newly generated audio.

Check identity, anatomy, hands, object contact, embedded text, transition logic, rapid movement, speaker attribution, dialogue accuracy, pronunciation, and lip synchronization. Longer or multi-shot scenes create more opportunities for temporal and character drift.

Explore Other Models

Discover more AI models for your next creative workflow

View all models

Kuaishou

Kling 3.0 Turbo

Kling 3.0 Turbo is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.

VideoNew

$0.112/sec

Kuaishou

Kling 2.6

Kling 2.6 is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.

VideoNew

$0.3/video

Kuaishou

Kling 2.5 Turbo Pro

Kling 2.5 Turbo Pro is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.

VideoNew

$0.3/video

xai

Grok Video

Grok Video is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.

VideoNew

$0.015/sec

ByteDance

Seedance 2.0

Seedance 2.0 is available on APIXO for Video. The model page brings examples, creation controls, pricing, and results into one focused workspace.

VideoNew

$0.0573/sec