@juspay/neurolink/dist/utils/mediaDuration.d.ts

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

/**
 * Shared duration formatting for the media processors.
 *
 * AudioProcessor and VideoProcessor each carried their own private
 * `formatDuration`, and they disagreed: the same two-second file rendered as
 * "0:02" from audio and "2s" from video, and a zero duration as "0:00" versus
 * "0s". Both strings land in the `textContent` handed to the model, often in
 * the same request when a video's muxed audio is described alongside it, so
 * the mismatch reads as two different facts about one file.
 *
 * The explicit-unit form wins over the "m:ss" clock form because these strings
 * are consumed by a language model, not rendered in a player scrubber: "1m 30s"
 * has exactly one reading, while "1:30" is ambiguous between 1m30s and 1h30m
 * and has to be disambiguated from context that may not be present.
 */
/**
 * Format a duration in seconds as explicit units — "45s", "1m 30s", "1h 2m 3s".
 *
 * Non-finite, negative and zero durations all render as "0s": callers reach
 * this with a probe failure or a stream that reports no duration, and a
 * fabricated number would be worse than an obvious zero.
 */
export declare function formatMediaDuration(seconds: number): string;
/**
 * Format the moment a video keyframe was sampled at — "3.00s",
 * "1234.00s (20m 34s)".
 *
 * Deliberately not the clock form, for the reason in this module's header:
 * the string is read by a language model, and "0:03" is ambiguous. That is
 * not theoretical here — an early draft labelled frames "0:03" and the model
 * reported the green frame as appearing at "3:00".
 *
 * Deliberately not `formatMediaDuration` alone either. That rounds to whole
 * seconds, and an explicit `videoOptions.frames` spreads frames evenly rather
 * than on the duration tier: sixteen frames across a 3.6s clip are 0.225s
 * apart, and every one of them would render as "0s". The precise value is
 * therefore always present, with the readable form added only past a minute,
 * where "1234.00s" stops meaning anything to a reader.
 *
 * Non-finite and negative inputs clamp to zero rather than emitting "NaNs".
 */
export declare function formatKeyframeTimestamp(seconds: number): string;