Karaoke subtitles | agent view

The same page content and links, with explicit tool capabilities. Tools marked with an API can run directly through HTTP. Other tools require the browser interface or are not connected yet.

Tool capabilities

{
  "id": "karaoke-subtitles",
  "category": "subtitle-tools",
  "built": true,
  "requirements": "Generate word-highlight timings from lyrics or a transcript; preview highlighting and export ASS. Singing and accompaniment must be separately evaluated.",
  "implementation": {
    "fields": [
      {
        "key": "transcript",
        "label": "Matching English transcript or lyrics",
        "type": "textarea",
        "value": ""
      }
    ],
    "files": true,
    "accept": ".wav,.mp3,.m4a,.flac,.mp4,.webm",
    "multiple": false,
    "input": false,
    "processing": "Server required",
    "native": true,
    "extra": true,
    "maxFileBytes": 20971520,
    "note": "Local Whisper forced alignment. English, up to one minute and 5,000 transcript characters. Review word timing; singing and overlapping voices may align poorly.",
    "experience": {
      "automatic": false,
      "single": false,
      "label": "Your text",
      "placeholder": "Type or paste your input…",
      "help": "Up to 1,000,000 characters. Review the settings before running.",
      "action": null
    },
    "mode": "explicit",
    "interactive": false
  },
  "execution": "POST /api/v1/tools/karaoke-subtitles/run",
  "api": {
    "id": "karaoke-subtitles",
    "name": "Karaoke subtitles",
    "category": "subtitle-tools",
    "description": "Create word-timed karaoke subtitles from matching speech and text.",
    "notes": "Local Whisper forced alignment. English, up to one minute and 5,000 transcript characters. Review word timing; singing and overlapping voices may align poorly.",
    "human_path": "/en/subtitle-tools/karaoke-subtitles/",
    "method": "POST",
    "endpoint": "/api/v1/tools/karaoke-subtitles/run",
    "schema_url": "/api/v1/tools/karaoke-subtitles",
    "input_schema": {
      "type": "object",
      "additionalProperties": false,
      "properties": {
        "input": {
          "type": "string",
          "maxLength": 1000000,
          "default": "",
          "description": "Plain text input. File tools use files instead unless otherwise documented."
        },
        "options": {
          "type": "object",
          "additionalProperties": false,
          "properties": {
            "transcript": {
              "type": "string",
              "description": "Matching English transcript or lyrics",
              "default": ""
            }
          }
        },
        "files": {
          "type": "array",
          "maxItems": 1,
          "items": {
            "type": "object",
            "required": [
              "name",
              "base64"
            ],
            "additionalProperties": false,
            "properties": {
              "name": {
                "type": "string",
                "maxLength": 200,
                "description": "Filename only, no path."
              },
              "mime": {
                "type": "string",
                "maxLength": 150
              },
              "bytes": {
                "type": "integer",
                "minimum": 0,
                "description": "Optional decoded byte count; must match content if supplied."
              },
              "base64": {
                "type": "string",
                "contentEncoding": "base64",
                "description": "File bytes as padded base64. Use the tool-specific limits.files_bytes value for the total decoded input size."
              }
            }
          }
        }
      }
    },
    "output_schema": {
      "type": "object",
      "required": [
        "tool",
        "result"
      ],
      "properties": {
        "tool": {
          "type": "string"
        },
        "result": {
          "type": "object",
          "required": [
            "text",
            "files"
          ],
          "properties": {
            "text": {
              "type": [
                "string",
                "null"
              ]
            },
            "data": {
              "description": "Parsed JSON when the textual result is JSON."
            },
            "name": {
              "type": "string"
            },
            "mime": {
              "type": "string"
            },
            "files": {
              "type": "array",
              "items": {
                "type": "object",
                "required": [
                  "name",
                  "mime",
                  "bytes",
                  "base64"
                ],
                "properties": {
                  "name": {
                    "type": "string"
                  },
                  "mime": {
                    "type": "string"
                  },
                  "bytes": {
                    "type": "integer"
                  },
                  "base64": {
                    "type": "string",
                    "contentEncoding": "base64"
                  }
                }
              }
            }
          }
        }
      }
    },
    "processing": "Server; self-hosted native engine, no external conversion service",
    "limits": {
      "request_bytes": 31457280,
      "input_characters": 1000000,
      "files_bytes": 20971520,
      "max_files": 1,
      "timeout_seconds": 90
    }
  },
  "agent_processing": "Server; self-hosted native engine, no external conversion service",
  "browser_agent": {
    "supported": true,
    "name": "run_current_tool",
    "discovery": "WebMCP on the human page in a supporting browser",
    "verification": "See audit/API-AUDIT.md; availability is not verification"
  }
}

Page guide

Create word-timed karaoke subtitles from matching speech and text.