@juspay/neurolink/dist/voice/streaming/endpointer.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

/**
 * Energy-gated endpointer for client-side streaming of batch STT engines.
 *
 * Pure and synchronous: feed it float samples at any input rate, get back
 * utterance start / end / drop events. It knows nothing about engines; the
 * chunked adapter decides what to transcribe and when.
 *
 * The rules and their constants were measured on live microphones and on a
 * 45 s three-speaker meeting slice, where they recover 155 of the 156 words a
 * batch transcription of the whole file finds (a plain fixed-threshold gate
 * recovered 125):
 *
 * - Work on 20 ms blocks.
 * - The noise floor is a minimum statistic — the quietest block of the last
 *   1.5 s — allowed to rise by at most ~2× per second and never below 0.0005.
 *   Because it follows the quietest block, a loud talker can never raise it
 *   enough to push a quieter second speaker below the gate.
 * - Hysteresis: speech starts above `max(onsetRms, floor × 3)` and is
 *   sustained above `max(onsetRms × 0.58, floor × 1.8)`, so soft word endings
 *   are kept inside the utterance instead of counting as silence.
 * - `prerollMs` of audio before the onset is kept, so the first consonant is
 *   not clipped.
 * - An utterance ends after `endSilenceMs` without sustained speech. One with
 *   less than `minSpeechMs` of speech is a cough and is dropped — unless a
 *   pass already heard words in it, which must never be lost.
 * - A long turn (`softCutSeconds`) ends at the next ≥ 320 ms gap; a turn with
 *   no gap at all is hard-cut at `maxUtteranceSeconds` at the quietest block
 *   of the last 3 s, and the remainder becomes the start of the next
 *   utterance, so no audio falls between the two.
 *
 * @module voice/streaming/endpointer
 */
import type { STTEndpointerConfig, STTEndpointerEvent, STTEndpointerUtterance, STTStreamingOptions } from "../../types/index.js";
/** Sample rate every engine pass receives. */
export declare const ENGINE_SAMPLE_RATE = 16000;
/** Defaults of `STTStreamingOptions` that the endpointer reads. */
export declare const ENDPOINTER_DEFAULTS: {
    readonly endSilenceMs: 750;
    readonly softCutSeconds: 16;
    readonly maxUtteranceSeconds: 28;
    readonly onsetRms: 0.006;
    readonly prerollMs: 350;
    readonly minSpeechMs: 250;
};
/** Applies the defaults to caller tuning; non-finite or non-positive values fall back. */
export declare function resolveEndpointerConfig(options: STTStreamingOptions | undefined, inputRate: number): STTEndpointerConfig;
export declare function rmsOf(samples: Float32Array): number;
/** Linear-interpolation resampler to 16 kHz; returns the input untouched when it already is. */
export declare function resampleTo16k(samples: Float32Array, inputRate: number): Float32Array;
export declare class Endpointer {
    readonly config: STTEndpointerConfig;
    private readonly blockLen;
    private block;
    private blockFill;
    private noise;
    private readonly noiseWin;
    private pre;
    private preLen;
    private utt;
    private seq;
    /** Input samples that went through the gate so far: the audio clock, in whole blocks. */
    private consumed;
    constructor(config: STTEndpointerConfig);
    /** The utterance being built, if speech is in progress. */
    get current(): STTEndpointerUtterance | null;
    /** Seconds of input consumed so far. */
    get audioSeconds(): number;
    /** Feeds samples at the input rate; returns the events they caused, in order. */
    push(samples: Float32Array): STTEndpointerEvent[];
    /**
     * Ends the stream: a partial block is folded into the open utterance, which
     * is then ended (`flush`) — or dropped when it is a cough nobody heard.
     */
    flush(): STTEndpointerEvent[];
    /** The utterance's audio at 16 kHz. */
    pcm16k(u: STTEndpointerUtterance): Float32Array;
    private sustainThreshold;
    private newUtterance;
    private onBlock;
    private hardCut;
}