LALAL.AI · Schema

LALAL.AI Split Task Result

Schema for a single source result returned from POST /api/v1/check/ for a LALAL.AI split, multistem, demuser, voice-clean, or change-voice task.

AIArtificial IntelligenceAudioAudio ProcessingStem SeparationVocal RemovalVoice CleaningVoice CloningVoice ChangerMusicMachine LearningDSP

Properties

Name	Type	Description
status	string	Lifecycle state of the split task.
task_id	string	Identifier returned from the original split request.
source_id	string	Identifier of the uploaded source file.
name	string	Original uploaded filename.
size	integer	Source file size in bytes.
duration	number	Source duration in seconds.
stem	string	Stem requested for extraction.
splitter	string	Neural network used to process the source.
encoder_format	string
progress	integer	Progress percentage when status is 'progress'.
split	object	Signed download URLs and metadata for the produced tracks.
error	object

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/lalal-ai/main/json-schema/lalal-ai-split-task-schema.json",
  "title": "LALAL.AI Split Task Result",
  "description": "Schema for a single source result returned from POST /api/v1/check/ for a LALAL.AI split, multistem, demuser, voice-clean, or change-voice task.",
  "type": "object",
  "required": ["status"],
  "properties": {
    "status": {
      "type": "string",
      "enum": ["success", "error", "progress", "cancelled"],
      "description": "Lifecycle state of the split task."
    },
    "task_id": {
      "type": "string",
      "description": "Identifier returned from the original split request."
    },
    "source_id": {
      "type": "string",
      "description": "Identifier of the uploaded source file."
    },
    "name": {
      "type": "string",
      "description": "Original uploaded filename."
    },
    "size": {
      "type": "integer",
      "minimum": 0,
      "description": "Source file size in bytes."
    },
    "duration": {
      "type": "number",
      "minimum": 0,
      "description": "Source duration in seconds."
    },
    "stem": {
      "type": "string",
      "enum": ["vocals", "voice", "drum", "bass", "piano", "electric_guitar", "acoustic_guitar", "synthesizer", "strings", "wind", "music"],
      "description": "Stem requested for extraction."
    },
    "splitter": {
      "type": "string",
      "enum": ["andromeda", "perseus", "orion", "phoenix", "lyra", "lynx", "auto"],
      "description": "Neural network used to process the source."
    },
    "encoder_format": {
      "type": "string",
      "enum": ["mp3", "wav", "flac", "aac", "ogg"]
    },
    "progress": {
      "type": "integer",
      "minimum": 0,
      "maximum": 100,
      "description": "Progress percentage when status is 'progress'."
    },
    "split": {
      "type": "object",
      "description": "Signed download URLs and metadata for the produced tracks.",
      "properties": {
        "stem_track": {"type": "string", "format": "uri"},
        "stem_track_size": {"type": "integer", "minimum": 0},
        "back_track": {"type": "string", "format": "uri"},
        "back_track_size": {"type": "integer", "minimum": 0}
      }
    },
    "error": {
      "type": "object",
      "properties": {
        "code": {"type": "string"},
        "message": {"type": "string"}
      }
    }
  },
  "additionalProperties": true
}