@juspay/neurolink/dist/types/transcribe.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

/**
 * `transcribe` — the fourth inference type, next to `generate`, `stream` and
 * `decide`. Turns audio into text through any registered STT handler, with the
 * optional layers that make self-hosted engines usable in production:
 *
 * - a dictionary of names and jargon, sent to the engine as context and used
 *   to repair mis-hearings after the fact;
 * - a decision-model guard (`tryDecide`) that asks, per dictionary candidate,
 *   whether the speaker meant the term or the literal word, so a name never
 *   rewrites the ordinary word it sounds like; fails open like every other
 *   `decide` consumer;
 * - an LLM rewrite (`generate`/`stream`) that fixes spelling and punctuation
 *   and writes Indic-script words in Latin letters the way people type
 *   (Hinglish, Tanglish …) without ever translating them;
 * - a second-opinion engine whose text the rewrite reconciles with the
 *   primary one, and a fallback engine for utterances the primary cannot read
 *   (an Indic model on English speech reports a low language score, or
 *   nothing at all);
 * - client-side streaming for batch engines: a chunked adapter with an energy
 *   gate, rolling re-transcription and LocalAgreement commits.
 *
 * Nothing in these layers may lose words: a rewrite that drops more than
 * `maxDropRatio` of them is discarded, a timed-out guard applies the dictionary
 * as is, and a final pass that returns less than the live text keeps the live
 * text.
 *
 * @module types/transcribe
 */
export {};