@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, STTHandler, STTLanguage, STTOptions, STTResult } from "../../types/index.js";
/**
 * OpenAI Whisper Speech-to-Text Handler
 *
 * Supports transcription and translation using OpenAI's Whisper model.
 *
 * @see https://platform.openai.com/docs/api-reference/audio
 */
export declare class OpenAISTT implements STTHandler {
    private readonly apiKey;
    private readonly baseUrl;
    /**
     * Maximum audio duration in seconds (25 minutes)
     */
    readonly maxAudioDuration: number;
    /**
     * Whisper does not support streaming
     */
    readonly supportsStreaming = false;
    constructor(apiKey?: string);
    isConfigured(): boolean;
    getSupportedFormats(): TTSAudioFormat[];
    getSupportedLanguages(): Promise<STTLanguage[]>;
    transcribe(audio: Buffer | ArrayBuffer, options?: STTOptions): Promise<STTResult>;
    /**
     * 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 };