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

/**
 * Deepgram Speech-to-Text Handler
 *
 * Implementation of STT using Deepgram's Speech Recognition API.
 *
 * @module voice/providers/DeepgramSTT
 */
import type { TTSAudioFormat, STTCredentials, STTHandler, STTLanguage, STTOptions, STTResult, TranscriptionSegment } from "../../types/index.js";
/**
 * Deepgram Speech-to-Text Handler
 *
 * Supports real-time streaming, speaker diarization, and smart formatting.
 *
 * @see https://developers.deepgram.com/docs
 */
export declare class DeepgramSTT implements STTHandler {
    private readonly apiKey;
    private readonly baseUrl;
    /**
     * Maximum audio duration in seconds (2 hours)
     */
    readonly maxAudioDuration = 7200;
    /**
     * Deepgram supports streaming
     */
    readonly supportsStreaming = true;
    /**
     * @param apiKeyOrCredentials - The `credentials.stt.deepgram` slice
     *   (`apiKey`, `baseURL`), or an API key (the original positional form).
     *   `DEEPGRAM_API_KEY` / `DEEPGRAM_BASE_URL` fill whatever is left out.
     */
    constructor(apiKeyOrCredentials?: string | STTCredentials["deepgram"]);
    /** The streaming endpoint: the REST base URL on the WebSocket scheme. */
    private get wsBaseUrl();
    /** A language the caller pinned, or `undefined` for "let Deepgram detect". */
    private static pinnedLanguage;
    isConfigured(): boolean;
    getSupportedFormats(): TTSAudioFormat[];
    getSupportedLanguages(): Promise<STTLanguage[]>;
    transcribe(audio: Buffer | ArrayBuffer, options?: STTOptions): Promise<STTResult>;
    /**
     * Streaming transcription using WebSocket
     */
    transcribeStream(audioStream: AsyncIterable<Buffer>, options: STTOptions): AsyncIterable<TranscriptionSegment>;
    /**
     * Timing, words and speaker of one live result, taken only from fields the
     * payload actually carries. The segment's speaker is its words' speaker
     * when they all agree.
     */
    private static streamSegmentDetails;
    /**
     * Get MIME type for audio format
     */
    private getMimeType;
}