Chaining clips across models
Pick the right model for each shot — dialogue, action, b-roll — then stitch the clips into one MP4 with Varosity's stitch step.
Chaining clips across models
The pitch: no single model is best at everything. Veo 3.1 owns lip-sync, Kling 3.0 owns cinematic motion, Seedance 2.0 owns audio-native generation (Seedance 1.0 Pro is silent), Runway Gen-4.5 owns camera control. Varosity lets you mix-and-match per shot.
A simple 4-shot example
| Shot | Type | Best model | Why |
| 01 | Wide establishing | Kling 3.0 Pro | cinematic motion, native audio |
| 02 | Talking close-up | Veo 3.1 | best lip-sync, native audio |
| 03 | Action beat | Seedance 1.0 Pro | multi-shot intent (silent) |
| 04 | Hero close-up | Runway Gen-4.5 (Replicate) | camera control |
Set up: 1. Create a project. 2. Click + Add your first shot, pick Kling, write the wide. 3. + Insert after, pick Veo for the dialogue, paste your line. 4. Repeat for shots 03 and 04. 5. Hit Render this shot + all downstream to fan out renders. 6. Once everything's done, Render final stitches into one MP4.
When you don't know which model to pick
There is no model-routing control in the studio inspector. Ask an agent
or the CLI instead: the MCP tool suggest_model and
varosity route suggest --shot "…" take a plain-English shot description
and rank candidate models with reasoning.
Cost discipline
The cost line in the inspector estimates per-shot at the registry's
pricePerSec. The gallery's Renders filter (/app/gallery) shows the
total spent per final cut. On BYOK there's no markup — what
fal/Replicate/etc. bill is what you pay; on Varosity Credits it is the
provider's list price.