deepsbhat1984/acappella-to-song

Public

18 runs

Run deepsbhat1984/acappella-to-song with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
audio	string		Raw a cappella vocal (just singing, no music). wav/mp3/m4a.
style	string	warm modern pop	Musical style for the band (e.g. 'warm pop', 'trap', 'acoustic ballad', 'r&b').
retune_strength	number	0 Max: 1	Pitch correction: 0 = untouched (most natural), 1 = hard tune. " "Keep low to avoid a robotic sound.
force_ambient	boolean	False	Skip the beat and always use the safe ambient bed (guaranteed in-time).
replicate_api_token	string		OPTIONAL. Leave blank - Replicate injects a token automatically " "so the engine can generate the instruments. Only paste your own " "r8_... token if the band step reports an auth error.

{
  "type": "object",
  "title": "Input",
  "required": [
    "audio"
  ],
  "properties": {
    "audio": {
      "type": "string",
      "title": "Audio",
      "format": "uri",
      "x-order": 0,
      "description": "Raw a cappella vocal (just singing, no music). wav/mp3/m4a."
    },
    "style": {
      "type": "string",
      "title": "Style",
      "default": "warm modern pop",
      "x-order": 1,
      "description": "Musical style for the band (e.g. 'warm pop', 'trap', 'acoustic ballad', 'r&b')."
    },
    "force_ambient": {
      "type": "boolean",
      "title": "Force Ambient",
      "default": false,
      "x-order": 3,
      "description": "Skip the beat and always use the safe ambient bed (guaranteed in-time)."
    },
    "retune_strength": {
      "type": "number",
      "title": "Retune Strength",
      "default": 0,
      "maximum": 1,
      "minimum": 0,
      "x-order": 2,
      "description": "Pitch correction: 0 = untouched (most natural), 1 = hard tune. \"\n                        \"Keep low to avoid a robotic sound."
    },
    "replicate_api_token": {
      "type": "string",
      "title": "Replicate Api Token",
      "format": "password",
      "x-order": 4,
      "nullable": true,
      "writeOnly": true,
      "description": "OPTIONAL. Leave blank - Replicate injects a token automatically \"\n                        \"so the engine can generate the instruments. Only paste your own \"\n                        \"r8_... token if the band step reports an auth error.",
      "x-cog-secret": true
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "object",
  "title": "Output",
  "required": [
    "song",
    "key",
    "scale",
    "bpm",
    "chords",
    "arrangement",
    "drift_score",
    "kept_real_voice",
    "debug"
  ],
  "properties": {
    "bpm": {
      "type": "integer",
      "title": "Bpm"
    },
    "key": {
      "type": "string",
      "title": "Key"
    },
    "song": {
      "type": "string",
      "title": "Song",
      "format": "uri"
    },
    "debug": {
      "type": "string",
      "title": "Debug"
    },
    "scale": {
      "type": "string",
      "title": "Scale"
    },
    "chords": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "title": "Chords"
    },
    "arrangement": {
      "type": "string",
      "title": "Arrangement"
    },
    "drift_score": {
      "type": "number",
      "title": "Drift Score"
    },
    "kept_real_voice": {
      "type": "boolean",
      "title": "Kept Real Voice"
    }
  }
}