stitch_video
ActiveTool of Hermoso
declared in 1.0.0
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.
Parameters schema
{
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"scenes"
],
"properties": {
"model": {
"type": "string",
"description": "video model id from hermoso_capabilities — omit to let the router pick"
},
"voice": {
"type": "string",
"description": "voiceover voice name, e.g. Rachel / George"
},
"scenes": {
"type": "array",
"items": {
"type": "object",
"properties": {},
"additionalProperties": {}
},
"minItems": 2,
"description": "array of scene objects (visual + optional voiceover/seconds)"
},
"voiceover": {
"type": "string",
"description": "full voiceover script spoken across the scenes"
},
"resolution": {
"type": "string",
"description": "720p (default), 480p draft, or 1080p final"
},
"aspectRatio": {
"type": "string",
"description": "output aspect ratio, e.g. 9:16 (default) / 1:1 / 16:9"
},
"durationSeconds": {
"type": "number",
"description": "total spot length in seconds (defaults to the sum of the scenes’ seconds)"
}
}
}No endpoints wrapped at confidence ≥ 0.50.
Parent server
Hermoso
https://github.com/hermoso-ai/hermoso
1/7 registries