The Podcast with me recipe is scenes you swap, not a new Omni board

/workflows/podcast-with-me is a locked scene list. Recreate it; do not storyboard it again in Kling Omni.

The public recipe is a two-person studio conversation: the host invites a guest and they talk. That is a scene graph — prompts, character stills, two rooms, a model — not a vibe. Opening Kling 3 Omni and asking for "six shots of a podcast" is a new film that happens to contain a microphone.

Four scenes, two chairs, one graph

The workflow object is specific:

• Aspect: 9:16
• Scenes: four, independent (chain_from_previous is false on every row)
• Cast and rooms: Podcast Host, Podcast Guest, Host View Studio, Guest View Studio — locked references, not "a guy in a booth"
• Scene list: Host Intro → Guest Response → Host Follow-up → Guest Conclusion
• Model on the recipe: Vidu Q3 Image to Video
• Credit estimate: 156 at preview resolution, 308 for the full-resolution render

Each scene is a pair: a still from the named refs, then that still animated, then a stitch. Host in the host-view studio. Guest in the guest-view studio. Medium shots. Same two people. Same two rooms. The scenes do not chain off the last frame — continuity is the references. That is why you swap stills instead of rewriting a storyboard. Read a workflow's credit estimate before you run it: scene count is not the bill. The video model is.

Recreate clones the table. Omni invents a bumper.

Recreate a viral template is the agent verb: browse the public catalog, clone scenes, style, and model into your account, then run or remix. Cloning is free. Running is priced like the generation it is. You see the cost before anything dispatches. It is saved but not auto-run — swap the host still, swap the guest, keep the cuts.

Recreate the workflow, not the screenshot is the same rule in conversion form. A screenshot of a podcast tells you the caption was big. It does not tell you Vidu Q3 Image to Video, the four scene names, the two studios, or 156 / 308 credits.

Kling 3 Omni multi-shot is not Movie Mode is the other confusion. Omni takes one prompt and returns up to six distinct shots inside a single generation, usually a 15-second file. You still pay for seconds. Identities have to survive inside that generate. There is no scene planner, no four discrete I2V scenes, no combined export of host-then-guest-then-host-then-guest with locked refs. You get one bumper with cuts in it.

Useful for a three-beat gag. Not useful for two locked people across two locked rooms. Omni restages. Restaging is drift. The workflow already named the people and attached their stills. This recipe is not Movie Mode either — chain_from_previous is false. Do not put a weekly podcast gag through a chained-film pipeline because it contains the word "conversation."

Swap the guest. Keep the cuts.

Once the format works, the workflow is the product. Clone it. Change the stills. Keep the intro / response / follow-up / conclusion, the medium shots, the two rooms. Do not go back to an Omni storyboard every Monday because the last clip performed.

If the clip you care about is not in /workflows, you do not have a recipe. Build one: stills first, then I2V, then save your graph. Vidu Q3 Image to Video is the spend on this recipe: image required, native audio, 5s / 10s / 15s, 1080p ceiling. Changing the model line changes the bill.

FAQ

Is Recreate the same as generating "podcast with me" in Omni?

No. Recreate clones the public workflow — four independent I2V scenes, host and guest refs, two studios, Vidu Q3 Image to Video, 156 credits at preview or 308 at full when you run it. Omni is one generate with internal cuts, typically ~15 seconds, up to six shots. Different objects. Different files.

Does cloning the podcast template spend the 156 credits?

No. Clone is free. Credits apply when you run it, at the cost shown before dispatch. Edit prompts and swap assets while it is still a draft.

Can I use Omni under the hood and keep the four-scene structure?

Not as this recipe. Omni multi-shot lives inside one short generate. Podcast with me is four discrete I2V scenes with locked refs, stitched, not chained off last frames. Even if a scene happened to render on a Kling family model, the object is still the scene list, not Omni storyboard syntax.

Why is a 4-scene recipe 156 / 308 when some longer recipes cost less?

Because the estimate is counting the video model, not the scene count. Vidu Q3 Image to Video across four scenes is a different unit from a cheaper I2V row across fifteen. Read the model line on the workflow page before you approve the run.