Which tools stop at 15 seconds per clip?
Nine vendors stop at 15 seconds or less, among them Kling, Grok Imagine, PixVerse and MiniMax at 15, Luma at 10, Google Veo at 8 and Pika's 5-second rows. From 4 source pages, read 2026-09-25 to 2026-10-25; no maker pays to be listed.
| Source | Figure | Where it applies |
|---|---|---|
| Grok Imagine | 1 to 15 seconds per video; edited videos keep their original length, capped at 8.7 seconds | Duration parameter |
| Kling AI | Up to 15 seconds of continuous video, flexible from 3 to 15 | VIDEO 3.0, 15-second generation |
| MiniMax | 4 to 15 seconds on MiniMax H3, whole seconds only | Output specs table |
| PixVerse | 1 to 15 seconds | V6, video duration row |
Inclusion rule. Vendor pages and references whose printed figures bear on this delivery target. Order. Alphabetical by source name.
1As printed
with a flexible duration ranging from 3 to 15 seconds.
Kling AI, VIDEO 3.0 model user guide
The allowed range is 1–15 seconds.
xAI docs, video generation
1-15 seconds
PixVerse platform docs, model capability map
Output duration 4–15 seconds, integer values only
MiniMax API platform, video generation guide
2What it means for delivery
Fifteen seconds is roughly two or three shots of drama. A clip ceiling this short makes the cut, not the model, the place where scenes are built.
No figure on longest single output from 3 vendors: DramaSo, Filmora and Runway.
- VIDEO 3.0Up to 15 seconds of continuous video, flexible from 3 to 1515-second generation
- Duration parameter1 to 15 seconds per video; edited videos keep their original length, capped at 8.7 seconds
- V61 to 15 secondsvideo duration row
- Output specs table4 to 15 seconds on MiniMax H3, whole seconds only
3How one pipeline outputs it
For a delivery question like “Which tools stop at 15 seconds per clip”, SceneMixer states the following about what it produces:
A short drama episode has two jobs: stop the scroll in its first seconds, and make the next episode feel necessary in its last.
SceneMixer, Writing Hooks and Cliffhangers Into a Short Drama Script (read 2026-10-13)
Dubbing replaces the audio of a finished clip; the picture was generated for a different line, so mouth shapes, pauses and shot length all belong to the original language. Native-language generation gives the video model the line in the target language before it renders the shot, so the performance, the pacing and the cut points are built for that language.
SceneMixer, Native-Language Dialogue vs. Dubbing in AI Video (2026): Why the Cast Should Speak the Line (read 2026-10-13)