AI models on Craze
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Every video, image, voice, music and sound model Craze can direct, with what each one makes and what it costs.
Starts at$0.074 per second of video
Kuaishou's breakthrough model for 1080p video and audio in a single pass. Generate video with synchronized sound without separate audio tools.
Recording separate video and audio, then syncing them manually, is a common workflow problem.
Instead of writing separate prompts for video and audio, you write one brief.
Kling 2.6 Pro outputs 1080p, which is sharp enough for most professional work.
Combining video and audio generation saves a production step.
Craze creatively jams, researches and plans with you.
Craze generates anything imaginable. Video, audio, music, motion graphics and more.
Craze watches your footage and builds a final cut. With a real editor if you need it.
Every model here runs on every Craze plan, including Free, and Craze can use a different one for each shot.
| Kling 2.6 ProKuaishou | Seedance 2.5ByteDance Seed Team | Seedance 2.0ByteDance Seed Team | Seedance 2.0 FastByteDance Seed Team | |
|---|---|---|---|---|
| Makes | Text + Image to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video | Text + Image + Video + Audio to video |
| Quality | Up to 1080p | Up to 1080p | Up to 4K | Up to 720p |
| Length | Up to 10s per clip | Up to 30s per clip | Up to 15s per clip | Up to 15s per clip |
| Sound | Generated with the picture | Generated with the picture | Generated with the picture | Generated with the picture |
| From | $0.074 per second of video | $0.114 per second of video | $0.075 per second of video | $0.06 per second of video |
| Task | Inputs | Resolution | Length | Aspect ratios | Sound |
|---|---|---|---|---|---|
| Image to video | First frame, Last frame | 1080p | 5, 10 s | Follows the input | On or off |
| Text to video | Text prompt | 1080p | 5 to 10 s | Follows the input | On or off |
$0/ month
$19/ month
$59/ month
$199/ month
Kling 2.6 Pro introduced something new to AI video: sound and picture generated in a single pass. That's faster than making video and scoring it separately, and it means the audio and visuals are inherently synchronized. For motion control, see Kling 3 Pro.
Recording separate video and audio, then syncing them manually, is a common workflow problem. Kling 2.6 Pro makes them at the same time. The audio and picture are aligned by construction.
Instead of writing separate prompts for video and audio, you write one brief. Kling 2.6 Pro understands the scene and generates matching sound. "A busy coffee shop with clinking cups and conversation" produces both the bustle and the visuals.
Kling 2.6 Pro outputs 1080p, which is sharp enough for most professional work. The audio can be ambient tone, sound effects, or music. You can always turn audio off if you want to add a voiceover or custom music in editing.
Combining video and audio generation saves a production step. Fewer passes means faster timelines and lower costs than generating video first, then scoring it separately.
The more you describe the sonic environment in your brief, the better the audio matches your intent. "Quiet office with keyboard clicks and distant city traffic" gives the model more to work with than "office sounds."
On Craze, Kling 2.6 Pro runs two core tasks, both generating 1080p output: text-to-video and image-to-video. Text-to-video clips range from 5 to 10 seconds, while image-to-video offers 5 or 10 seconds on Craze. Both tasks generate audio alongside video, with audio as an optional toggle.
Text-to-video accepts a written prompt and generates 1080p video with sound that matches the scene. Describing the sonic environment in your prompt helps Kling 2.6 Pro generate appropriate audio. Image-to-video starts with a static image and extends it into motion, also producing coordinated sound.
Unlike Kling 3.0 models, Kling 2.6 Pro does not accept video input or offer motion transfer. Its focused strength is combining video and audio generation in one pass.
Kling 2.6 Pro bills per second of video. $0.074 per second of video The rate is higher than Kling 2.5 Turbo Pro because audio generation is included by default. On Craze, audio is optional, so toggling it off and generating silent video reduces the per-second cost.
Clip length is the primary cost driver: a 5-second clip costs less than a 10-second clip. Enabling audio adds substantial cost compared to silent generation.
Use the cost calculator on this page to compare the cost of generating with audio versus silent and plan your project accordingly.
If you spend time sourcing, recording, or layering ambient audio, Kling 2.6 Pro saves that production step. The model handles sound design as part of video generation, producing coordinated audio that matches the scene.
Commercials, explainer videos, and branded content often need precisely coordinated sound and picture. Kling 2.6 Pro generates them together automatically, ensuring sync and coherence. No need to export video and score it separately in an audio editor.
When the sound of a place matters to immersion, Kling 2.6 Pro excels. A hospital has its distinctive acoustic signature (monitors, ventilation, hushed voices), a forest has ambient sound (wind, birds, rustling leaves), and a factory has mechanical rhythm. Kling 2.6 Pro understands these sonic environments and generates matching audio.
Content creators who produce podcasts or written-word video essays can use Kling 2.6 Pro to generate B-roll with ambient sound, then mix it behind their voiceover in the edit. The generated audio provides texture without competing with the human voice.
Teams that need to produce video content quickly benefit from native audio generation. One generation pass replaces two separate passes (video, then audio), saving time and credits.
Kling 2.6 Pro generates 1080p with native audio and supports image input. Kling 2.5 Turbo Pro generates 1080p but is text-only with no audio. Kling 2.6 Pro costs more because it handles audio. Choose Kling 2.6 Pro when native sound matters. Choose 2.5 Turbo Pro for silent clips.
Kling 3.0 models support video input and include motion transfer, which Kling 2.6 does not. Kling 2.6 Pro's strength is simultaneous audio-visual generation in a single pass. If native audio is your priority, choose Kling 2.6 Pro. If motion transfer or video input matters, choose Kling 3 Pro.
Describe what you want the way you would brief an editor, and Craze plans the shots and writes the Kling 2.6 Pro prompts for you. Every Craze plan, including Free, runs Kling 2.6 Pro and every other media model, and Craze can use a different one for each job. Each video lands on an editable timeline with your cuts, captions and music, ready to export as MP4. Generations come out of your plan's monthly credits, from $0.074 per second of video, with top-ups when you need more.
Creators who want finished sound design: If you spend time sourcing, recording, or layering ambient audio, Kling 2.6 Pro saves that production step. Broadcast and commercial work: Commercials, explainer videos, and branded content often need precisely coordinated sound and picture. Narrative and scene-based video: When the sound of a place matters to immersion, Kling 2.6 Pro excels. Podcast and video essay B-roll: Content creators who produce podcasts or written-word video essays can use Kling 2.6 Pro to generate B-roll with ambient sound, then mix it behind their voiceover in the edit.
Kling 2.6 Pro is Kuaishou's 1080p video generation model with native audio. It generates sound and picture together in a single pass, not separately.
Kuaishou released Kling 2.6 Pro on December 3, 2025, introducing simultaneous audio-visual generation to the Kling model family.
Kling 2.6 Pro generates both video and audio at the same time, syncing them automatically. You don't write separate audio prompts or layer sound after the fact. One prompt produces coordinated picture and sound.
Kling 2.6 Pro generates 1080p video. For 720p, use Kling 3 Standard. For 4K, use Kling 3 4K or Kling O3 4K. For ultra-low cost, use Kling 2.5 Turbo Pro.
Kling 2.6 Pro accepts text prompts and image references. One generation can use both together.
On Craze, text-to-video clips range from 5 to 10 seconds. Image-to-video offers 5 or 10 seconds. For longer content, generate multiple clips and cut them together.
Yes. On Craze, audio is optional. You can generate sound with the video or create a silent clip and add your own music or voiceover later.
Kling 2.6 Pro costs $0.074 per second of video on Craze. Sound is optional and the rate changes when you enable it. Use the cost calculator on this page for your specific clip.
every Craze plan, including Free include Kling 2.6 Pro.
ByteDance Seed Team
From $0.114 per second of video
ByteDance Seed Team
From $0.075 per second of video
ByteDance Seed Team
From $0.06 per second of video
