LALAL.AI

aid: lalal-ai
url: https://raw.githubusercontent.com/api-evangelist/lalal-ai/refs/heads/main/apis.yml
apis:
  - aid: lalal-ai:lalal-ai-api
    name: LALAL.AI API
    tags:
      - AI
      - Audio
      - Stem Separation
      - Voice Cloning
      - Music
      - Vocal Removal
      - Machine Learning
    humanURL: https://www.lalal.ai/api/
    baseURL: https://www.lalal.ai
    properties:
      - url: https://www.lalal.ai/api/
        type: Documentation
      - url: https://www.lalal.ai/api/v1/docs/
        type: Documentation
        name: API v1 Reference (Swagger)
      - url: https://www.lalal.ai/api/v1/openapi.json
        type: OpenAPISource
        name: Official OpenAPI v1 JSON
      - url: https://www.lalal.ai/blog/meet-lalal-ai-api-v1/
        type: Blog
        name: Meet LALAL.AI API v1
      - url: https://github.com/OmniSaleGmbH/lalalai
        type: GitHubRepository
        name: Official API Examples
      - url: openapi/lalal-ai-api-openapi.yml
        type: OpenAPI
      - url: json-schema/lalal-ai-split-task-schema.json
        type: JSONSchema
      - url: json-schema/lalal-ai-upload-schema.json
        type: JSONSchema
      - url: json-schema/lalal-ai-voice-pack-schema.json
        type: JSONSchema
      - url: json-ld/lalal-ai-context.jsonld
        type: JSONLD
      - url: examples/lalal-ai-upload-example.json
        type: Example
      - url: examples/lalal-ai-split-stem-separator-example.json
        type: Example
      - url: examples/lalal-ai-check-example.json
        type: Example
      - url: examples/lalal-ai-multistem-example.json
        type: Example
      - url: examples/lalal-ai-change-voice-example.json
        type: Example
      - url: rules/lalal-ai-rules.yml
        type: Spectral
      - url: vocabulary/lalal-ai-vocabulary.yml
        type: Vocabulary
    description: >-
      LALAL.AI API v1 is a production-grade audio separation, voice cleaning, and voice cloning API powered by
      proprietary neural networks (Andromeda, Perseus, Orion, Phoenix, Lyra, Lynx). It exposes upload, split,
      multi-stem, demuser, voice-clean, change-voice, voice-pack listing, task polling, and limits endpoints with both
      single-task and batch variants. Authentication is via the X-License-Key header. Supported stems include vocals,
      drums, bass, piano, electric guitar, acoustic guitar, synthesizer, strings, and wind, with output in MP3, WAV,
      FLAC, AAC, or OGG.
common:
  - type: Portal
    url: https://www.lalal.ai
  - type: Documentation
    url: https://www.lalal.ai/api/
  - type: Documentation
    url: https://www.lalal.ai/api/v1/docs/
  - type: GettingStarted
    url: https://www.lalal.ai/api/help/
  - type: Pricing
    url: https://www.lalal.ai/pricing/
  - type: Blog
    url: https://www.lalal.ai/blog/
  - type: Changelog
    url: https://www.lalal.ai/changelog/
  - type: Support
    url: https://www.lalal.ai/support/
  - type: TermsOfService
    url: https://www.lalal.ai/terms-of-service/
  - type: PrivacyPolicy
    url: https://www.lalal.ai/privacy-policy/
  - type: GitHubOrganization
    url: https://github.com/OmniSaleGmbH
  - type: GitHubRepository
    url: https://github.com/OmniSaleGmbH/lalalai
    name: Official LALAL.AI API Examples (Python)
  - type: ContactUs
    url: mailto:[email protected]
  - type: SDK
    url: https://github.com/OmniSaleGmbH/lalalai/tree/main/api-v1/python
    name: Python Example Client
  - type: Plans
    url: plans/lalal-ai-plans-pricing.yml
  - type: RateLimits
    url: rate-limits/lalal-ai-rate-limits.yml
  - type: FinOps
    url: finops/lalal-ai-finops.yml
  - type: Features
    data:
      - >-
        Six proprietary neural networks: Andromeda (6th-gen, 2025), Perseus (transformer), Orion, Phoenix, Lyra
        (dereverb / demuser), and Lynx
      - >-
        Stem separation for vocals, drum, bass, piano, electric guitar, acoustic guitar, synthesizer, strings, and wind
        instruments
      - Single-task and batch (multi-file) variants for stem_separator, demuser, and voice_clean endpoints
      - Multistem endpoint extracts up to six stems in a single request
      - Demuser endpoint isolates music from non-music components
      - >-
        Voice Clean endpoint removes background music and ambient noise from spoken-word audio with 3-level noise
        cancelling
      - >-
        Change Voice endpoint applies legal artist Voice Packs (ALEX_KAYE, STASIA_FAYE, NICOLAAS_HAAS, NIK_ZEL,
        OLIA_CHEBO, YVAR_DE_GROOT, VETRANA) or user-trained custom Voice Packs from the Voice Cloner
      - Voice Packs list endpoint returns user-trained packs with previews, language metadata, and ready-to-use state
      - >-
        Dereverb option for vocals/voice stems plus accent intensity, pitch shifting, and tonality reference controls
        for voice conversion
      - Lead/back vocal splitter via the multivocal parameter on stem separation
      - >-
        Asynchronous job model — POST returns task_id, poll /check/ for progress (success, progress, error, cancelled)
        and signed download URLs for stem_track and back_track
      - Cancel individual tasks or all running tasks; delete uploaded source files
      - Limits endpoint returns remaining processing minutes and the plan tier
      - Output formats MP3, WAV, FLAC, AAC, OGG (defaults to source format)
      - Extraction levels Clear Cut and Deep Extraction on Perseus
      - File upload via single-PUT or multipart for large files (up to 10 GB with valid license)
      - 24-hour retention on uploaded source files
      - Official OpenAPI 3.1 spec served at /api/v1/openapi.json with Swagger-style explorer at /api/v1/docs/
      - Official Python example client maintained at github.com/OmniSaleGmbH/lalalai
      - API access included on Pro and higher plans, with custom enterprise pricing available
    sources:
      - https://www.lalal.ai/api/
      - https://www.lalal.ai/api/v1/docs/
      - https://www.lalal.ai/api/v1/openapi.json
      - https://www.lalal.ai/pricing/
      - https://www.lalal.ai/changelog/
      - https://www.lalal.ai/blog/meet-lalal-ai-api-v1/
      - https://github.com/OmniSaleGmbH/lalalai
    updated: '2026-05-25'
name: LALAL.AI
created: '2026-05-25T00:00:00.000Z'
modified: '2026-05-25'
position: Producing
description: >-
  LALAL.AI is an AI-powered audio separation and voice technology platform operated by OmniSale GmbH. It uses
  proprietary neural networks (Andromeda, Perseus, Orion, Phoenix, Lyra, Lynx) to isolate vocals, instruments, drums,
  bass, guitars, piano, synth, strings, and wind from mixed audio, clean voice recordings, and clone or convert voices
  with consent. The company ships a web app, native desktop, iOS and Android apps, a VST plug-in for DAWs, and a
  production REST API (v1) for embedding stem separation and voice cloning into third-party SaaS, media, and
  post-production pipelines.
image: https://www.lalal.ai/static/images/og/preview.png
tags:
  - AI
  - Artificial Intelligence
  - Audio
  - Audio Processing
  - Stem Separation
  - Vocal Removal
  - Voice Cleaning
  - Voice Cloning
  - Voice Changer
  - Music
  - Machine Learning
  - DSP
maintainers:
  - FN: Kin Lane
    email: [email protected]
    X: apievangelist
    url: https://apievangelist.com
specificationVersion: '0.16'