Toono
Flexible Kling video model

Direct a longer Kling shot with optional audio

Use Kling V3 for text-led or image-led clips with flexible 3–15 second duration, social formats, standard or pro output, and an optional generated audio track.

Open Kling V3 Video

Open video generation with this model selected

See examples and review points
The workspace offers 3–15 seconds, 720p or 1080p, optional audio, and a last frame when a starting image is used.
The workspace offers 3–15 seconds, 720p or 1080p, optional audio, and a last frame when a starting image is used.

Visual examples

Choose only the controls that help the story

Kling V3 adds text input, flexible duration, audio, and end-frame options beyond the V2.1 image-only path.

Kling V3 preview — Judge narrative timing, consistency, shot changes, motion, and audio.KwaiVGI

Kling V3 preview

Judge narrative timing, consistency, shot changes, motion, and audio.

Kling V2.1 baseline — Use the simpler image-first option for a short animation.KwaiVGI

Kling V2.1 baseline

Use the simpler image-first option for a short animation.

Review generated audio separately for speech, timing, ambience, effects, pronunciation, and unwanted sound.

Kuaishou Kling 3.0 announcement
Practical workflow

Plan picture, timing, and sound as one sequence

A 15-second ceiling still benefits from a simple action arc and clear final beat.

  1. 01

    Choose text or image

    Use text for a new scene or image for a fixed opening and subject.

  2. 02

    Write visual and audio beats

    Describe action, camera, pace, ambience, speech, or effects.

  3. 03

    Review tracks separately

    Watch once for visuals, once for audio, and once for synchronization.

Kling V3 Video questions

Capabilities and production choices in the current Toono AI integration.

Related products

Compare simpler motion or richer reference workflows

Kling V2.1, Grok Imagine, and Veo 3.1 balance input, timing, and audio differently.

Kling V2.1 — Image-to-video Kling model with standard or pro mode, 5s or 10s duration, and optional end frame control.
KwaiVGI

Kling V2.1

Image-to-video Kling model with standard or pro mode, 5s or 10s duration, and optional end frame control.

View product page
Grok Imagine Video — xAI video model for text, image, and video-driven generation with flexible 1s to 15s timing and lightweight per-second pricing.
xAI

Grok Imagine Video

xAI video model for text, image, and video-driven generation with flexible 1s to 15s timing and lightweight per-second pricing.

View product page
Veo 3.1 — Premium video model with 4s, 6s, and 8s generations, optional audio, and support for multiple reference images.
Google

Veo 3.1

Premium video model with 4s, 6s, and 8s generations, optional audio, and support for multiple reference images.

View product page

Shot brief ready

Direct the first Kling V3 sequence

Test one coherent visual and audio arc before expanding the prompt.

Open Kling V3 Video

Open video generation with this model selected