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

/**
 * OpenAI Whisper Speech-to-Text Handler
 *
 * Implementation of STT using OpenAI's Whisper model.
 *
 * @module voice/providers/OpenAISTT
 */
import type { TTSAudioFormat, STTCredentials, STTHandler, STTLanguage, STTOptions, STTResult } from "../../types/index.js";
export declare class OpenAISTT implements STTHandler {
    private readonly apiKey;
    private readonly baseUrl;
    private readonly defaultTimeoutMs;
    /** The `model` sent when the request names none. */
    private readonly defaultModel;
    /**
     * Maximum audio duration in seconds (25 minutes)
     */
    readonly maxAudioDuration: number;
    /**
     * Whisper does not support streaming
     */
    readonly supportsStreaming = false;
    /**
     * @param apiKeyOrCredentials - The `credentials.stt.whisper` slice
     *   (`apiKey`, `baseURL`, `timeoutMs`), or — the original positional form —
     *   an API key. Anything left out falls back to the environment.
     * @param baseUrl - Base URL, positional form only.
     */
    constructor(apiKeyOrCredentials?: string | STTCredentials["whisper"], baseUrl?: string);
    /** True when pointed at OpenAI itself rather than a compatible server. */
    private get isOfficialEndpoint();
    /**
     * OpenAI itself needs a key. A compatible server at another base URL may
     * not (a self-hosted engine on the local network), so a base URL alone
     * configures the handler and the request goes without an Authorization header.
     */
    isConfigured(): boolean;
    getSupportedFormats(): TTSAudioFormat[];
    getSupportedLanguages(): Promise<STTLanguage[]>;
    transcribe(audio: Buffer | ArrayBuffer, options?: STTOptions): Promise<STTResult>;
    /**
     * The context prompt: the caller's own text, then the vocabulary as one
     * sentence. Whisper-style decoders treat the prompt as preceding text, so a
     * plain list of names biases spelling without being read as an instruction.
     */
    private static buildPrompt;
    /**
     * Optional language-identification fields a self-hosted server may add to
     * `verbose_json`. Each is read only when it has the expected shape; a
     * server that sends none (OpenAI itself) contributes nothing.
     */
    private static readLanguageExtensions;
    /**
     * Get MIME type for audio format. Whisper auto-detects from headers, but
     * sending a correct MIME helps providers / proxies that sniff Content-Type.
     * Must stay aligned with `getSupportedFormats()`.
     */
    private getMimeType;
}
export { OpenAISTT as WhisperSTT };
export { OpenAISTT as WhisperSTTHandler };
export { OpenAISTT as OpenAISTTHandler };