@juspay/neurolink/dist/types/avatar.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

/**
 * Avatar / Lip-sync Type Definitions
 *
 * Types for generating talking-head videos by combining a portrait image
 * with narration audio (or text routed through a TTS provider first).
 *
 * Avatar is a separate modality from Video — Video is image-to-video
 * (motion synthesis); Avatar is image + audio → lip-synced video.
 *
 * @module types/avatar
 */
/**
 * Valid avatar video formats — runtime validation array.
 */
export const VALID_AVATAR_FORMATS = [
    "mp4",
    "webm",
    "mov",
];