Picture and sound in one pass
Kandinsky 6.0 generates the video and a 44 kHz audio track together, so footsteps, rain, music and voices land on the action. Write the sound into the same prompt as the picture.
Start Creating NowKandinsky 6.0 AI Video Generator
Text or image to video with synchronized sound and lip-sync, from the new open Kandinsky 6.0 models
Strictly Prohibits Adult/NSFW ContentCREATECreate a Kandinsky 6.0 video
LiveChoose modelCompatible models · settings update automatically
Only live routes are selectable. Your prompt stays in place when you switch.
This generation−5creditsCost guide
Your video will appear here
What Is Kandinsky 6.0?
Kandinsky 6.0 is the new video generation family from Kandinsky Lab, released as open weights under the MIT license on October 6, 2026. Kandinsky 6.0 generates picture and sound together: every clip is 5 seconds at 24 fps with a synchronized 44 kHz audio track, including dialogue with lip-sync, ambience and effects. Kandinsky 6.0 Lite (3B parameters) is fast and inexpensive; Kandinsky 6.0 Pro (29B parameters) is the flagship for cinematic detail. On Kandinsky6.pro you can run both Kandinsky 6.0 models from a text prompt or a start image, upscale to 1080p, see the credit quote before each take and keep every video in your history.
5 s + audioEvery clip has synchronized sound
Lite 3B / Pro 29BTwo Kandinsky 6.0 model sizes
480p / 1080pBase render or super-resolution
1 free videoAfter sign-in, one per network
Kandinsky 6.0 Features
Three ways Kandinsky 6.0 gives you more control over the result you walk away with.
Dialogue with lip-sync
Put a short spoken line in quotes and say who speaks it. Kandinsky 6.0 voices the line and moves the speaker’s mouth with it, which makes quick talking-head clips and ads possible from one prompt.
Lite for speed, Pro for detail
Kandinsky 6.0 Lite (3B) is tuned for fast, low-cost drafts. Kandinsky 6.0 Pro (29B) adds detail, lighting and steadier motion for the take you keep. Both start from text or a start image.
Why Choose Kandinsky 6.0?
Kandinsky 6.0 comes in two sizes with one architecture and one output format. Pick Kandinsky 6.0 Lite to explore ideas quickly and Kandinsky 6.0 Pro when a shot needs more detail and stronger motion.
Kandinsky 6.0 Lite
3B parameters, fast drafts
5 credits for a 5-second 480p clip with audio; 10 credits at 1080p.
Kandinsky 6.0 Pro
29B parameters, flagship quality
40 credits for a 5-second 480p clip with audio; 45 credits at 1080p.
Output
5 s, 24 fps, 44 kHz audio
Every Kandinsky 6.0 clip has the same length and frame rate; 1080p comes from the Kandinsky 6.0 super-resolution model.
Inputs
Text, or a start image
Image-to-video keeps your picture as the first frame and picks the closest supported aspect ratio.
How to Generate an AI Video with Kandinsky 6.0
- 01
Pick Lite or Pro
Start with Kandinsky 6.0 Lite for quick drafts, or choose Kandinsky 6.0 Pro for the final take. Upload a start image to switch to image-to-video.
- 02
Write picture and sound
Subject and action first, then camera and light, then the sound. Put dialogue in quotes and name the speaker.
- 03
Choose format and quality
Pick 16:9, 9:16, 1:1, 4:3 or 3:4, and 480p or 1080p. The exact credit quote updates before you submit.
- 04
Play, download, iterate
Watch the Kandinsky 6.0 clip with sound, download the MP4 and change one detail for the next take.
What Can You Make With Kandinsky 6.0?
Working prompt structures with the result they produced. Swap the subject, keep the direction concrete, and adapt them to your own brief.
Dialogue with lip-sync
One short line in quotes, who says it and the sound around them is enough for Kandinsky 6.0 Pro to voice the line and move the speaker’s mouth with it.
An astronaut in a white suit stands in a red desert canyon on Mars, turns toward the camera and says through the helmet radio: "We found water." Dust drifts past. Medium close-up, slow push in. Sound: radio-filtered voice, breathing in the helmet, low wind.
Vertical music clips
Pick 9:16, name the instrument and the place, and Kandinsky 6.0 Lite plays the music in step with the hands on screen.
Vertical phone video: a street musician plays an acoustic guitar on a rainy city corner at night, neon reflections on wet pavement, people with umbrellas pass by. Sound: warm fingerpicked guitar melody, rain, passing footsteps.
Clear Pricing. Automatic Failure Refunds.
See the credit cost before every generation, then choose a subscription or a one-time top-up when you need more.
Start here
Free video
Sign in and make one Kandinsky 6.0 Lite video free.
Freeto start
5 welcome credits
Estimated capacityUp to 1 minimum-cost 5s videoFrom 5 credits per 5s video
- 5 welcome credits, one per network
- One 5-second 480p Kandinsky 6.0 Lite video
- Synchronized audio included
- Private generation history
- Failed jobs return credits automatically
Most popular
Creator
For regular individual creative work.
$29/ month
120 credits / month
$0.242 / credit
Estimated capacityUp to 24 minimum-cost 5s videosFrom 5 credits per 5s video
- 120 credits every month
- Credits roll over
- Generation history
- Cancel anytime
Monthly plan
Studio
For campaigns and higher-volume production.
$79/ month
330 credits / month
$0.239 / credit
Estimated capacityUp to 66 minimum-cost 5s videosFrom 5 credits per 5s video
- 330 credits every month
- Credits roll over
- Generation history
- Email support
Monthly plan
Max
For larger workloads, with adjustable credit capacity.
$158/ month
660 credits / month
$0.239 / credit
Estimated capacityUp to 132 minimum-cost 5s videosFrom 5 credits per 5s video
- Monthly credit grant
- Scale up to 5x credits
- Credits roll over
- Generation history
- Email support
- Cancel anytime
Plans are shown for launch preparation. Checkout opens after production checks are complete.
Kandinsky 6.0 FAQ
What is Kandinsky 6.0?
Kandinsky 6.0 is a family of video generation models from Kandinsky Lab that create video and synchronized audio together. It was open-sourced under the MIT license on October 6, 2026, in two sizes: Kandinsky 6.0 Lite (3B) and Kandinsky 6.0 Pro (29B).
Is Kandinsky 6.0 free?
The Kandinsky 6.0 weights are free to download under MIT, but running them needs a large NVIDIA GPU. On Kandinsky6.pro, eligible new accounts get 5 welcome credits once (one per network), enough for one 5-second Kandinsky 6.0 Lite video. More videos use paid credits.
Does Kandinsky 6.0 generate sound?
Yes. Every Kandinsky 6.0 clip includes a synchronized 44 kHz audio track with ambience, effects, music or speech. You can turn audio off in the studio; the credit price stays the same.
Can Kandinsky 6.0 do lip-sync?
Yes. Write the spoken line in quotes and say who speaks it. Kandinsky 6.0 voices the line and animates the speaker’s mouth. Short lines work best within the 5-second clip.
How long are Kandinsky 6.0 videos?
Every Kandinsky 6.0 video is 5 seconds at 24 fps (121 frames). Longer or shorter clips are not offered by the model.
What is the difference between Kandinsky 6.0 Lite and Pro?
Both share one architecture and output format. Lite has 3B parameters and is fast and cheap; Pro has 29B parameters and gives more detail and steadier motion at a higher credit cost.
Can I start from an image?
Yes. Upload a start image you have permission to use and Kandinsky 6.0 animates it, with sound, from your prompt.
Is there a Kandinsky 6.0 image model?
Kandinsky Lab announced Kandinsky 6.0 Image in April 2026. This studio runs the Kandinsky 6.0 video models; image generation is not offered here.
What happens if a generation fails?
Credits are reserved when a request starts. Confirmed failed jobs return them automatically; a job still being checked stays pending until it is reconciled.
Is Kandinsky6.pro the official Kandinsky site?
No. Kandinsky6.pro is an independent studio that runs the public Kandinsky 6.0 models through fal. It is not affiliated with or endorsed by Kandinsky Lab or Sber. The official project is at kandinskylab.ai.
Make your first Kandinsky 6.0 video
Create Kandinsky 6.0 videos with synchronized audio online. Run Kandinsky 6.0 Lite or Pro from text or an image, in 480p or 1080p, with one free video after sign-in.
Start Creating Now