@lakshmiprasanth/react-voice-to-text/lib/browser.d.ts

A modern React package for voice-to-text conversion with real-time speech recognition and file upload support

import React$1, { ReactNode } from 'react';

/**
 * Simple EventEmitter implementation for browser compatibility
 */
declare class EventEmitter {
    private events;
    on(event: string, listener: Function): this;
    once(event: string, listener: Function): this;
    off(event: string, listener: Function): this;
    emit(event: string, ...args: any[]): boolean;
    removeAllListeners(event?: string): this;
}
/**
 * Configuration options for speech recognition engines
 */
interface SpeechRecognitionConfig {
    /** Language code (e.g., 'en-US', 'es-ES') */
    language?: string;
    /** Sample rate for audio processing */
    sampleRate?: number;
    /** Enable continuous recognition */
    continuous?: boolean;
    /** Return interim results */
    interimResults?: boolean;
    /** Maximum number of alternatives to return */
    maxAlternatives?: number;
    /** Confidence threshold (0-1) */
    confidenceThreshold?: number;
    /** Custom vocabulary or phrases to improve recognition */
    phrases?: string[];
    /** Audio encoding format */
    encoding?: 'LINEAR16' | 'FLAC' | 'MULAW' | 'AMR' | 'AMR_WB' | 'OGG_OPUS' | 'SPEEX_WITH_HEADER_BYTE';
}
/**
 * Speech recognition result
 */
interface SpeechRecognitionResult {
    /** Transcribed text */
    transcript: string;
    /** Confidence score (0-1) */
    confidence: number;
    /** Whether this is a final result */
    isFinal: boolean;
    /** Alternative transcriptions */
    alternatives?: Array<{
        transcript: string;
        confidence: number;
    }>;
    /** Timestamp information */
    timestamp?: {
        start: number;
        end: number;
    };
}
/**
 * Audio input source configuration
 */
interface AudioInputConfig {
    /** Audio source type */
    source: 'microphone' | 'file' | 'stream';
    /** File path (for file source) */
    filePath?: string;
    /** Audio stream (for stream source) */
    audioStream?: NodeJS.ReadableStream;
    /** Device ID (for microphone source) */
    deviceId?: string;
    /** Recording duration in milliseconds (for microphone) */
    duration?: number;
}
/**
 * Engine-specific configuration
 */
interface EngineConfig {
    /** Engine type */
    engine: 'web-speech' | 'vosk' | 'google-cloud' | 'whisper';
    /** API key (for cloud services) */
    apiKey?: string;
    /** Model path (for offline engines like Vosk) */
    modelPath?: string;
    /** Project ID (for Google Cloud) */
    projectId?: string;
    /** Custom endpoint URL */
    endpoint?: string;
}
/**
 * Error types that can occur during speech recognition
 */
declare enum SpeechRecognitionErrorType {
    NO_SPEECH = "no-speech",
    ABORTED = "aborted",
    AUDIO_CAPTURE = "audio-capture",
    NETWORK = "network",
    NOT_ALLOWED = "not-allowed",
    SERVICE_NOT_ALLOWED = "service-not-allowed",
    BAD_GRAMMAR = "bad-grammar",
    LANGUAGE_NOT_SUPPORTED = "language-not-supported",
    ENGINE_ERROR = "engine-error",
    INVALID_CONFIG = "invalid-config"
}
/**
 * Speech recognition error
 */
declare class SpeechRecognitionError extends Error {
    type: SpeechRecognitionErrorType;
    originalError?: Error | undefined;
    constructor(type: SpeechRecognitionErrorType, message: string, originalError?: Error | undefined);
}
/**
 * Events emitted by speech recognition engines
 */
interface SpeechRecognitionEvents {
    'start': () => void;
    'result': (result: SpeechRecognitionResult) => void;
    'end': () => void;
    'error': (error: SpeechRecognitionError) => void;
    'audiostart': () => void;
    'audioend': () => void;
    'soundstart': () => void;
    'soundend': () => void;
    'speechstart': () => void;
    'speechend': () => void;
    'initialized': () => void;
    'started': () => void;
    'stopped': () => void;
}
/**
 * Base interface for speech recognition engines
 */
interface ISpeechRecognitionEngine extends EventEmitter {
    /** Start speech recognition */
    start(audioConfig: AudioInputConfig, recognitionConfig?: SpeechRecognitionConfig): Promise<void>;
    /** Stop speech recognition */
    stop(): Promise<void>;
    /** Abort speech recognition */
    abort(): Promise<void>;
    /** Check if engine is available */
    isAvailable(): boolean;
    /** Get supported languages */
    getSupportedLanguages(): string[];
    /** Process audio file directly */
    processFile(file: File, config?: SpeechRecognitionConfig): Promise<SpeechRecognitionResult[]>;
    /** Process audio stream */
    processStream(stream: NodeJS.ReadableStream, config?: SpeechRecognitionConfig): Promise<SpeechRecognitionResult[]>;
}
/**
 * Voice-to-text converter options
 */
interface VoiceToTextOptions {
    /** Default engine configuration */
    defaultEngine?: EngineConfig;
    /** Default speech recognition configuration */
    defaultRecognitionConfig?: SpeechRecognitionConfig;
    /** Enable automatic engine fallback */
    enableFallback?: boolean;
    /** Engine priority order for fallback */
    enginePriority?: Array<EngineConfig['engine']>;
    /** Debug mode */
    debug?: boolean;
}
/**
 * Microphone recording options
 */
interface MicrophoneOptions {
    /** Recording duration in milliseconds */
    duration?: number;
    /** Device ID to use */
    deviceId?: string;
    /** Sample rate */
    sampleRate?: number;
    /** Number of channels */
    channels?: number;
    /** Bit depth */
    bitDepth?: number;
    /** Audio format */
    format?: 'wav' | 'raw';
}
/**
 * Browser compatibility information
 */
interface BrowserSupport {
    /** Whether Web Speech API is supported */
    webSpeechAPI: boolean;
    /** Whether MediaRecorder API is supported */
    mediaRecorder: boolean;
    /** Whether getUserMedia is supported */
    getUserMedia: boolean;
    /** Browser name and version */
    browser: {
        name: string;
        version: string;
    };
}
/**
 * Props for VoiceRecorder component
 */
interface VoiceRecorderProps {
    /** CSS class name */
    className?: string;
    /** Whether to show language selector */
    showLanguageSelector?: boolean;
    /** Whether to show results display */
    showResults?: boolean;
    /** Whether to show recording controls */
    showControls?: boolean;
    /** Default language */
    language?: string;
    /** Enable continuous recording */
    continuous?: boolean;
    /** Show interim results */
    interimResults?: boolean;
    /** Callback when result is received */
    onResult?: (result: SpeechRecognitionResult) => void;
    /** Callback when error occurs */
    onError?: (error: string) => void;
    /** Callback when recording starts */
    onStart?: () => void;
    /** Callback when recording stops */
    onStop?: () => void;
    /** Child components */
    children?: React.ReactNode;
}
/**
 * Props for FileUpload component
 */
interface FileUploadProps {
    /** CSS class name */
    className?: string;
    /** Callback when file is selected */
    onFileSelect?: (file: File) => void;
    /** Callback when file is converted */
    onConvert?: (file: File, language: string) => Promise<void>;
    /** Callback when error occurs */
    onError?: (error: string) => void;
    /** Accepted file formats */
    acceptedFormats?: string[];
    /** Maximum file size in bytes */
    maxFileSize?: number;
    /** Whether to show language selector */
    showLanguageSelector?: boolean;
    /** Default language */
    language?: string;
    /** Enable drag and drop */
    dragAndDrop?: boolean;
    /** Allow multiple file selection */
    multiple?: boolean;
    /** Whether component is disabled */
    disabled?: boolean;
    /** Child components */
    children?: React.ReactNode;
}
/**
 * Props for ResultsDisplay component
 */
interface ResultsDisplayProps {
    /** Array of recognition results */
    results: SpeechRecognitionResult[];
    /** Error message */
    error?: string | null;
    /** Callback to clear results */
    onClear?: () => void;
    /** Whether to show clear button */
    showClearButton?: boolean;
    /** Whether to show confidence scores */
    showConfidence?: boolean;
    /** Whether to show status (final/interim) */
    showStatus?: boolean;
    /** Maximum number of results to display */
    maxResults?: number;
    /** CSS class name */
    className?: string;
    /** Text to show when no results */
    emptyText?: string;
}
/**
 * Props for LanguageSelector component
 */
interface LanguageSelectorProps {
    /** Selected language value */
    value?: string;
    /** Callback when language changes */
    onChange?: (language: string) => void;
    /** Whether component is disabled */
    disabled?: boolean;
    /** CSS class name */
    className?: string;
    /** Whether to show label */
    showLabel?: boolean;
    /** Label text */
    label?: string;
    /** Placeholder text */
    placeholder?: string;
}
/**
 * Props for RecordingControls component
 */
interface RecordingControlsProps {
    /** Whether currently recording */
    isRecording: boolean;
    /** Whether currently processing */
    isProcessing: boolean;
    /** Callback to start recording */
    onStart?: () => void;
    /** Callback to stop recording */
    onStop?: () => void;
    /** Whether component is disabled */
    disabled?: boolean;
    /** CSS class name */
    className?: string;
    /** Whether to show status */
    showStatus?: boolean;
    /** Text for start button */
    startText?: string;
    /** Text for stop button */
    stopText?: string;
    /** Text for processing state */
    processingText?: string;
}

interface VoiceToTextContextType {
    isInitialized: boolean;
    isRecording: boolean;
    isProcessing: boolean;
    results: SpeechRecognitionResult[];
    error: string | null;
    browserSupport: BrowserSupport | null;
    startRecording: (options?: Partial<SpeechRecognitionConfig>) => Promise<void>;
    stopRecording: () => Promise<void>;
    clearResults: () => void;
    clearError: () => void;
    updateConfig: (config: Partial<VoiceToTextOptions>) => void;
    getConfig: () => VoiceToTextOptions;
}
interface VoiceToTextProviderProps {
    children: ReactNode;
    options?: VoiceToTextOptions;
    onResult?: (result: SpeechRecognitionResult) => void;
    onError?: (error: string) => void;
    onStart?: () => void;
    onStop?: () => void;
}
declare const VoiceToTextProvider: React$1.FC<VoiceToTextProviderProps>;
declare const useVoiceToTextContext: () => VoiceToTextContextType;

declare const VoiceRecorder: React$1.FC<VoiceRecorderProps>;

declare const FileUpload: React$1.FC<FileUploadProps>;

interface VoiceToTextConverterProps {
    className?: string;
    showFileUpload?: boolean;
    showVoiceRecorder?: boolean;
    showResults?: boolean;
    defaultLanguage?: string;
    onResult?: (result: SpeechRecognitionResult) => void;
    onError?: (error: string) => void;
    onStart?: () => void;
    onStop?: () => void;
    children?: React$1.ReactNode;
}
declare const VoiceToTextConverter: React$1.FC<VoiceToTextConverterProps>;

declare const ResultsDisplay: React$1.FC<ResultsDisplayProps>;

declare const LanguageSelector: React$1.FC<LanguageSelectorProps>;

declare const RecordingControls: React$1.FC<RecordingControlsProps>;

interface UseVoiceToTextOptions extends VoiceToTextOptions {
    onResult?: (result: SpeechRecognitionResult) => void;
    onError?: (error: string) => void;
    onStart?: () => void;
    onStop?: () => void;
}
interface UseVoiceToTextReturn {
    isInitialized: boolean;
    isRecording: boolean;
    isProcessing: boolean;
    results: SpeechRecognitionResult[];
    error: string | null;
    browserSupport: BrowserSupport | null;
    startRecording: (options?: Partial<SpeechRecognitionConfig>) => Promise<void>;
    stopRecording: () => Promise<void>;
    clearResults: () => void;
    clearError: () => void;
    updateConfig: (config: Partial<VoiceToTextOptions>) => void;
    getConfig: () => VoiceToTextOptions;
}
declare const useVoiceToText: (options?: UseVoiceToTextOptions) => UseVoiceToTextReturn;

interface UseVoiceRecorderOptions {
    language?: string;
    continuous?: boolean;
    interimResults?: boolean;
    onResult?: (result: any) => void;
    onError?: (error: string) => void;
    onStart?: () => void;
    onStop?: () => void;
}
interface UseVoiceRecorderReturn {
    isInitialized: boolean;
    isRecording: boolean;
    isProcessing: boolean;
    results: any[];
    error: string | null;
    startRecording: () => Promise<void>;
    stopRecording: () => Promise<void>;
    clearResults: () => void;
    clearError: () => void;
}
declare const useVoiceRecorder: (options?: UseVoiceRecorderOptions) => UseVoiceRecorderReturn;

interface UseFileUploadOptions {
    acceptedFormats?: string[];
    maxFileSize?: number;
    onFileSelect?: (file: File) => void;
    onConvert?: (file: File, language: string) => Promise<any>;
    onError?: (error: string) => void;
}
interface UseFileUploadReturn {
    selectedFile: File | null;
    isConverting: boolean;
    results: any[];
    error: string | null;
    selectFile: (file: File) => void;
    convertFile: (language?: string) => Promise<void>;
    clearFile: () => void;
    clearResults: () => void;
    clearError: () => void;
    validateFile: (file: File) => {
        isValid: boolean;
        error?: string;
    };
}
declare const useFileUpload: (options?: UseFileUploadOptions) => UseFileUploadReturn;

interface UseSpeechRecognitionOptions {
    language?: string;
    continuous?: boolean;
    interimResults?: boolean;
    maxAlternatives?: number;
    onResult?: (event: any) => void;
    onError?: (event: any) => void;
    onStart?: () => void;
    onEnd?: () => void;
    onAudioStart?: () => void;
    onAudioEnd?: () => void;
    onSoundStart?: () => void;
    onSoundEnd?: () => void;
    onSpeechStart?: () => void;
    onSpeechEnd?: () => void;
    onNoMatch?: () => void;
    onNomatch?: () => void;
}
interface UseSpeechRecognitionReturn {
    isSupported: boolean;
    isListening: boolean;
    transcript: string;
    finalTranscript: string;
    interimTranscript: string;
    error: string | null;
    start: () => void;
    stop: () => void;
    abort: () => void;
    reset: () => void;
    updateConfig: (config: Partial<UseSpeechRecognitionOptions>) => void;
}
declare const useSpeechRecognition: (options?: UseSpeechRecognitionOptions) => UseSpeechRecognitionReturn;

/**
 * Check browser support for speech recognition and related APIs
 */
declare function getBrowserSupport(): BrowserSupport;
/**
 * Get available audio input devices
 */
declare function getAudioDevices(): Promise<MediaDeviceInfo[]>;
/**
 * Request microphone permission
 */
declare function requestMicrophonePermission(): Promise<boolean>;

/**
 * Supported audio file formats
 */
declare const SUPPORTED_AUDIO_FORMATS: string[];
/**
 * Check if a file is a supported audio format
 */
declare function isSupportedAudioFormat(filePath: string): boolean;

/**
 * Check browser capabilities for speech recognition
 * @returns Browser support information
 */
declare function checkBrowserSupport(): BrowserSupport;
declare const VERSION = "1.0.0";

declare global {
    interface Window {
        ReactVoiceToText: {
            VoiceToTextConverter: typeof VoiceToTextConverter;
            VoiceRecorder: typeof VoiceRecorder;
            FileUpload: typeof FileUpload;
            useVoiceToText: typeof useVoiceToText;
            useVoiceRecorder: typeof useVoiceRecorder;
            checkBrowserSupport: typeof checkBrowserSupport;
            getAudioDevices: typeof getAudioDevices;
            requestMicrophonePermission: typeof requestMicrophonePermission;
        };
    }
}

export { EventEmitter, FileUpload, LanguageSelector, RecordingControls, ResultsDisplay, SUPPORTED_AUDIO_FORMATS, SpeechRecognitionError, SpeechRecognitionErrorType, VERSION, VoiceRecorder, VoiceToTextConverter, VoiceToTextProvider, checkBrowserSupport, VoiceToTextConverter as default, getAudioDevices, getBrowserSupport, isSupportedAudioFormat, requestMicrophonePermission, useFileUpload, useSpeechRecognition, useVoiceRecorder, useVoiceToText, useVoiceToTextContext };
export type { AudioInputConfig, BrowserSupport, EngineConfig, FileUploadProps, ISpeechRecognitionEngine, LanguageSelectorProps, MicrophoneOptions, RecordingControlsProps, ResultsDisplayProps, SpeechRecognitionConfig, SpeechRecognitionEvents, SpeechRecognitionResult, VoiceRecorderProps, VoiceToTextOptions };