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

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

/**
 * 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;
    };
}
/**
 * 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;
}
/**
 * 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;
}
/**
 * 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;
    };
}

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;

export { useFileUpload, useSpeechRecognition, useVoiceRecorder, useVoiceToText };