waveframe-webmcp.netlify.app

{
  "name": "get_project_state",
  "kind": "answer",
  "impl": "imperative",
  "description": "Inspect the current audio project state, timeline tracks, clips, ducking settings, master volume, and imported/generated assets.",
  "inputSchema": {
    "type": "object",
    "properties": {}
  }
}

{
  "name": "list_video_assets",
  "kind": "answer",
  "impl": "imperative",
  "description": "Discover and list all local video assets currently available in the project media library with their basic dimensions and durations.",
  "inputSchema": {
    "type": "object",
    "properties": {}
  }
}

{
  "name": "get_video_metadata",
  "kind": "answer",
  "impl": "imperative",
  "description": "Inspect detailed technical metadata of a specific video asset, including dimensions, duration, frame rate, mime type, size, and audio track status.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "assetId": {
        "type": "string",
        "description": "The unique ID of the target video asset."
      }
    },
    "required": [
      "assetId"
    ]
  }
}

{
  "name": "get_video_asset",
  "kind": "answer",
  "impl": "imperative",
  "description": "Resolve a structured local reference for an uploaded video asset (returns asset metadata and storage reference, not raw binary).",
  "inputSchema": {
    "type": "object",
    "properties": {
      "assetId": {
        "type": "string",
        "description": "The unique ID of the target video asset."
      }
    },
    "required": [
      "assetId"
    ]
  }
}

{
  "name": "extract_video_audio",
  "kind": "act",
  "impl": "imperative",
  "description": "Extract the audio soundtrack locally from a video asset into a 16-bit PCM WAV audio asset, making it available for editing, playback, and Whisper transcription.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "assetId": {
        "type": "string",
        "description": "The unique ID of the target video asset to extract audio from."
      }
    },
    "required": [
      "assetId"
    ]
  }
}

{
  "name": "get_video_transcript",
  "kind": "answer",
  "impl": "imperative",
  "description": "Retrieve an existing speech-to-text transcript associated with a video asset or its extracted audio. If none exists, returns a structured error instructing to run transcription.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "assetId": {
        "type": "string",
        "description": "The unique ID of the target video asset."
      }
    },
    "required": [
      "assetId"
    ]
  }
}

{
  "name": "get_video_frame",
  "kind": "answer",
  "impl": "imperative",
  "description": "Capture an image frame snapshot from a video asset at a specific timestamp using browser Canvas rendering.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "assetId": {
        "type": "string",
        "description": "The unique ID of the target video asset."
      },
      "timeSec": {
        "type": "number",
        "description": "Timestamp in seconds at which to capture the frame. Defaults to 0."
      }
    },
    "required": [
      "assetId"
    ]
  }
}

{
  "name": "transcribe_audio_asset",
  "kind": "act",
  "impl": "imperative",
  "description": "Run in-browser Whisper Speech-to-Text inference on a specific audio asset to produce timestamped transcription segments.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "assetId": {
        "type": "string",
        "description": "The unique ID of the target audio asset."
      },
      "language": {
        "type": "string",
        "description": "Language code for transcription (e.g. \"en\", \"es\", \"fr\"). Defaults to \"en\"."
      }
    },
    "required": [
      "assetId"
    ]
  }
}

{
  "name": "generate_voiceover",
  "kind": "act",
  "impl": "imperative",
  "description": "Synthesize a vocal narration track from text using multi-timbre neural speech generation and automatically add to timeline.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "text": {
        "type": "string",
        "description": "The narration or script text to synthesize."
      },
      "voiceId": {
        "type": "string",
        "description": "Voice persona: \"narrator_male\", \"narrator_female\", \"energetic_launch\", or \"executive_calm\"."
      },
      "speed": {
        "type": "number",
        "description": "Speech speed multiplier (0.5 to 1.75). Defaults to 1.0."
      },
      "pitch": {
        "type": "number",
        "description": "Pitch adjustment factor (0.75 to 1.25). Defaults to 1.0."
      },
      "autoInsertToTimeline": {
        "type": "boolean",
        "description": "Whether to immediately place the generated voiceover clip onto the Voiceover Track."
      }
    },
    "required": [
      "text"
    ]
  }
}

{
  "name": "generate_music",
  "kind": "act",
  "impl": "imperative",
  "description": "Generate a stereo backing track with synthesized bass, chords, arps, and percussion matching the requested mood.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "prompt": {
        "type": "string",
        "description": "Text description of the desired music backing track."
      },
      "mood": {
        "type": "string",
        "enum": [
          "energetic_tech",
          "cinematic_reveal",
          "ambient_minimal",
          "upbeat_fun"
        ],
        "description": "Mood harmonic preset."
      },
      "durationSec": {
        "type": "number",
        "description": "Length of the generated track in seconds (10 to 120). Defaults to 30."
      },
      "bpm": {
        "type": "number",
        "description": "Tempo in BPM (70 to 160). Defaults to 120."
      },
      "autoInsertToTimeline": {
        "type": "boolean",
        "description": "Whether to place the clip onto the Backing Music Track."
      }
    },
    "required": [
      "prompt"
    ]
  }
}

{
  "name": "update_audio_track",
  "kind": "act",
  "impl": "imperative",
  "description": "Modify track or clip positioning, gain, mute, or solo states on the timeline.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "clipId": {
        "type": "string",
        "description": "The ID of the clip to adjust."
      },
      "startSec": {
        "type": "number",
        "description": "New start timestamp in seconds on the timeline."
      },
      "gainDb": {
        "type": "number",
        "description": "Gain adjustment in decibels (e.g. -6 for -6dB)."
      },
      "trackId": {
        "type": "string",
        "description": "Target track ID for track-level adjustments."
      },
      "muted": {
        "type": "boolean",
        "description": "Set track mute state."
      },
      "solo": {
        "type": "boolean",
        "description": "Set track solo state."
      }
    }
  }
}

{
  "name": "mix_audio_project",
  "kind": "act",
  "impl": "imperative",
  "description": "Configure sidechain music ducking amount and master bus gain for the project mix.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "duckingAmountDb": {
        "type": "number",
        "description": "Decibels to attenuate music during voiceover (e.g. -14 for -14dB). Range: -30 to -3."
      },
      "masterGain": {
        "type": "number",
        "description": "Master output bus linear volume (0.0 to 1.5)."
      }
    }
  }
}

{
  "name": "export_audio",
  "kind": "act",
  "impl": "imperative",
  "description": "Render the full multi-track project with volume curves and sidechain ducking into a 16-bit PCM WAV master file.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "format": {
        "type": "string",
        "enum": [
          "wav"
        ],
        "description": "Audio format. Defaults to \"wav\"."
      }
    }
  }
}