Now on Runway
Kling 3.0
Kling's most advanced video generation, on Runway. Turn text prompts and images into video with native audio and speech — with start/end frame control and multi-shot sequences.
How to use Kling 3.0 on Runway
Start from text or an image
Write a prompt to generate from scratch, or upload an image to animate. Pin the first and last frames with images to control exactly where the motion starts and ends.
Choose your tier and settings
Pick Kling 3.0 Standard for budget-friendly generations, Pro for the most advanced output with audio and speech, or Turbo when speed matters most.
Generate with sound
Hit Generate and your video comes back with audio built in — dialogue, ambience and effects — ready to download and share.
What you can do with Kling 3.0
Native audio and speech
Generate dialogue, ambient sound and effects together with your visuals — no separate audio pass needed.
Start and end frame control
Pin the first and last frames with images and let Kling 3.0 fill in the motion between them.
Multi-shot sequences
Direct multi-shot videos that hold characters and style consistent across cuts.
Generate your first Kling 3.0 video on Runway.
Try nowMore models on Runway
Runway gives you access to the world's leading video, image and audio models — Runway's own frontier models plus the best from Google, OpenAI, Kling, ByteDance and more — all in one workspace.
Kling O3
Multi-modal video with audio, keyframes and up to 4K output.
Explore the model
Veo 3.1
Google's cinematic video generation with native audio and speech.
Explore the model
Seedance 2.0
Multi-modal video generation with sound from text, images, video or audio.
Explore the model
Aleph 2.0
Runway's flagship in-context video editing model — change only what you ask for.
Explore the model
Try Kling 3.0 on Runway today.
Video with native audio and speech, alongside every other leading AI model — in one workspace.
Try now
