Stitch multi-scene video
stitch_videoCombine multiple scenes into a single video for ads longer than 15 seconds. Specify scenes, voiceover, resolution, and aspect ratio to create a stitched ad.
Instructions
Render a multi-scene STITCHED video (≥2 scenes) — ONLY for spots LONGER than one model clip (>15s). A ≤15s multi-beat ad renders better and cheaper as ONE single-pass generate_video/render_ad on seedance-2 (it handles the full hook→demo→payoff arc in one take) — never stitch those. Blocks until done. Spends credits.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | video model id from hermoso_capabilities — omit to let the router pick | |
| voice | No | voiceover voice name, e.g. Rachel / George | |
| scenes | Yes | array of scene objects (visual + optional voiceover/seconds) | |
| voiceover | No | full voiceover script spoken across the scenes | |
| resolution | No | 720p (default), 480p draft, or 1080p final | |
| aspectRatio | No | output aspect ratio, e.g. 9:16 (default) / 1:1 / 16:9 | |
| durationSeconds | No | total spot length in seconds (defaults to the sum of the scenes’ seconds) |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| raw | No | the raw job result payload (e.g. images[] for carousel template ads) | |
| url | No | the served URL of the finished media (absent/null while still rendering) | |
| jobId | No | the render job id — poll get_job with this id to resume or inspect | |
| model | No | the product-facing label of the model that rendered it | |
| stillRendering | No | true when the render is still in progress — keep polling get_job with jobId |