fix_beat

Active

declared in 1.0.0

Surgically re-render ONE time window (1.5-8s) of an existing rendered video and splice it back on the VIDEO TRACK ONLY — the rest of the video and ALL audio stay byte-identical. Use when one beat/shot is broken ('the shot at 8 seconds glitches') and a full re-render would waste the parts that worked; bills only the replacement clip's seconds (~1/3 of a full render). Do NOT pick a window covering spoken dialogue (a video-only splice under speech breaks lip-sync) — pass speechWindows to enforce this.

Parameters schema

{
  "type": "object",
  "$schema": "http://json-schema.org/draft-07/schema#",
  "required": [
    "videoUrl",
    "startSeconds",
    "endSeconds",
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "description": "what the replacement footage should show — describe the shot, matching the master's style"
    },
    "refImage": {
      "type": "string",
      "description": "optional product/style anchor image URL"
    },
    "videoUrl": {
      "type": "string",
      "description": "the served URL of the master video to fix"
    },
    "endSeconds": {
      "type": "number",
      "description": "window end in seconds (window 1.5-8s)"
    },
    "startSeconds": {
      "type": "number",
      "description": "window start in seconds"
    },
    "speechWindows": {
      "type": "array",
      "items": {
        "type": "array",
        "items": {
          "type": "number"
        }
      },
      "description": "[[start,end],...] windows with spoken lines — the fix window must not overlap these"
    }
  }
}

What this tool wraps· 0 endpoints

min confidence0.70 0.50

No endpoints wrapped at confidence ≥ 0.50.

Parent server

Hermoso

https://github.com/hermoso-ai/hermoso

1/7 registries

View full server →