@juspay/neurolink/dist/types/music.js

The pipe layer of an AI nervous system: one interface connecting provider neurons to your application, across three inference types — generate, stream and decide. `decide` returns typed, calibrated judgements from a non-generative model (~400ms, ~$0.00002

/**
 * Music Generation Type Definitions
 *
 * Types for music / sound-effect generation across providers (Beatoven,
 * ElevenLabs Music, Lyria, Replicate-hosted MusicGen / Riffusion / AudioGen).
 *
 * Music is a separate modality from TTS — TTS produces voiced speech with
 * prosody; Music produces melodic / harmonic / textural audio.
 *
 * @module types/music
 */
/**
 * Valid music audio formats — runtime validation array.
 */
export const VALID_MUSIC_FORMATS = [
    "mp3",
    "wav",
    "flac",
    "ogg",
];