@juspay/neurolink/dist/voice/providers/AzureSTT.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

/**
 * Azure Cognitive Services Speech-to-Text Handler
 *
 * Implementation of STT using Azure Speech Services.
 *
 * @module voice/providers/AzureSTT
 */
import type { TTSAudioFormat, STTHandler, STTLanguage, STTOptions, STTResult, TranscriptionSegment } from "../../types/index.js";
/**
 * Azure Cognitive Services Speech-to-Text Handler
 *
 * Supports speech recognition with custom models and detailed output.
 *
 * @see https://docs.microsoft.com/azure/cognitive-services/speech-service/
 */
export declare class AzureSTT implements STTHandler {
    private readonly apiKey;
    private readonly region;
    /**
     * Maximum audio duration in seconds (60s — Azure's REST API for short audio
     * documented limit on `/speech/recognition/conversation/cognitiveservices/v1`).
     * For longer audio, use Azure Batch Transcription (not yet implemented) or
     * pre-segment the input.
     */
    readonly maxAudioDuration = 60;
    /**
     * Azure STT implementation buffers chunks via REST — not true streaming
     */
    readonly supportsStreaming = false;
    constructor(apiKey?: string, region?: string);
    isConfigured(): boolean;
    getSupportedFormats(): TTSAudioFormat[];
    getSupportedLanguages(): Promise<STTLanguage[]>;
    transcribe(audio: Buffer | ArrayBuffer, options?: STTOptions): Promise<STTResult>;
    /**
     * Streaming transcription (placeholder - requires SDK)
     */
    transcribeStream(audioStream: AsyncIterable<Buffer>, options: STTOptions): AsyncIterable<TranscriptionSegment>;
    /**
     * Get Content-Type header for audio format
     */
    private getContentType;
    /**
     * Convert Azure ticks (100ns units) to seconds
     */
    private ticksToSeconds;
}