Kling 2.6 Model
Overview
Kling 2.6 is a text‑to‑video model that can generate clips with or without sound. In StoryFlow, it is ideal for scripted scenes such as live‑shopping, explainers, and talking‑head content.
Capabilities
- Text‑to‑Video: Generate videos purely from a written script.
- Optional Sound: Control whether the output contains an audio track.
Inputs
- Text (Prompt): Include both visual directions and dialog, for example “the host turns to show the hoodie, then speaks this line”.
Parameters
| Parameter | Type | Default | Allowed | What it does |
|---|---|---|---|---|
aspectRatio | string | 16:9 | 1:1, 16:9, 9:16 | Sets output aspect ratio. |
duration | string | 5 | 5, 10 | Sets duration in seconds. |
sound | boolean | false | true, false | Enables generating a video with an audio track. |
Tips
- Great for promotional clips, live‑stream style shots, and product demos with spoken lines.
- Make prompts explicit about who is speaking, their tone, and the intended camera framing.
- If you plan to do heavy post‑production on the soundtrack, you can generate silent videos and add music or VO in external tools.