audiopod-sdk

/** * AudioPod SDK Types * Type definitions for the AudioPod API */ interface AudioPodConfig { apiKey: string; baseURL?: string; timeout?: number; maxRetries?: number; debug?: boolean; } interface ApiResponse<T = any> { data?: T; error?: string; message?: string; status?: string; } interface Job { id: number; status: JobStatus; progress: number; createdAt: string; updatedAt?: string; completedAt?: string; errorMessage?: string; parameters?: Record<string, any>; result?: Record<string, any>; } declare enum JobStatus { PENDING = "pending", PROCESSING = "processing", COMPLETED = "completed", FAILED = "failed", CANCELLED = "cancelled" } interface VoiceProfile { id: number; uuid: string; name: string; displayName?: string; description?: string; voiceType: VoiceType; provider: TTSProvider; isPublic: boolean; languageCode?: string; languageName?: string; gender?: string; accent?: string; createdAt?: string; status?: JobStatus; } declare enum VoiceType { CUSTOM = "custom", STANDARD = "standard" } declare enum TTSProvider { AUDIOPOD_SONIC = "audiopod_sonic", OPENAI = "openai", GOOGLE_GEMINI = "google_gemini" } interface VoiceCloneRequest { voiceFile: File | Blob | string; text: string; language?: string; speed?: number; waitForCompletion?: boolean; timeout?: number; } interface VoiceCloneResult { job: Job; outputUrl?: string; duration?: number; } interface MusicGenerationRequest { prompt: string; duration?: number; guidanceScale?: number; numInferenceSteps?: number; seed?: number; displayName?: string; waitForCompletion?: boolean; timeout?: number; } interface MusicGenerationResult { job: Job; outputUrl?: string; outputUrls?: Record<string, string>; audioDuration?: number; actualSeeds?: number[]; shareToken?: string; shareUrl?: string; isShared?: boolean; } interface TranscriptionRequest { audioFile: File | Blob | string; language?: string; modelType?: 'whisperx' | 'faster-whisper'; enableSpeakerDiarization?: boolean; enableWordTimestamps?: boolean; waitForCompletion?: boolean; timeout?: number; } interface TranscriptionResult { job: Job; transcript?: string; detectedLanguage?: string; confidenceScore?: number; segments?: TranscriptionSegment[]; audioDuration?: number; } interface TranscriptionSegment { text: string; start: number; end: number; speaker?: string; confidence?: number; } interface TranslationRequest { audioFile: File | Blob | string; targetLanguage: string; sourceLanguage?: string; waitForCompletion?: boolean; timeout?: number; } interface TranslationResult { job: Job; sourceLanguage?: string; targetLanguage?: string; audioOutputUrl?: string; videoOutputUrl?: string; transcriptPath?: string; transcriptUrls?: { json?: string; source_audio?: string; }; } interface CreditInfo { balance: number; paygBalance: number; totalAvailableCredits: number; nextResetDate?: string; totalCreditsUsed: number; } interface CreditUsageRecord { id: string; creditsUsed: number; serviceType: string; audioDuration: number; jobId?: string; creditSource: string; createdAt: string; usageMetadata?: Record<string, any>; } interface AudioPodError { message: string; code?: string; statusCode?: number; details?: Record<string, any>; } interface UploadProgress { loaded: number; total: number; percentage: number; } interface JobProgress { jobId: number; status: JobStatus; progress: number; message?: string; result?: any; } interface UseAudioPodOptions { apiKey?: string; onProgress?: (progress: JobProgress) => void; onError?: (error: AudioPodError) => void; onSuccess?: (result: any) => void; } interface UseVoiceCloningOptions extends UseAudioPodOptions { autoStart?: boolean; pollInterval?: number; } interface UseMusicGenerationOptions extends UseAudioPodOptions { autoStart?: boolean; pollInterval?: number; } interface UseTranscriptionOptions extends UseAudioPodOptions { autoStart?: boolean; pollInterval?: number; } interface AudioPodEvent { type: string; data: any; timestamp: string; } interface JobStatusEvent extends AudioPodEvent { type: 'job_status'; data: { jobId: number; status: JobStatus; progress: number; result?: any; }; } interface ProgressEvent extends AudioPodEvent { type: 'progress'; data: { jobId: number; progress: number; message?: string; }; } interface StemExtractionRequest { audioFile?: File | Blob | string; url?: string; stemTypes?: ('vocals' | 'drums' | 'bass' | 'other' | 'piano' | 'guitar')[]; modelName?: 'htdemucs' | 'htdemucs_6s'; twoStemsMode?: string; waitForCompletion?: boolean; timeout?: number; } interface StemExtractionResult { job: Job; stemPaths?: Record<string, string>; downloadUrls?: Record<string, string>; qualityScores?: Record<string, number>; } interface RapGenerationRequest { prompt: string; lyrics: string; duration?: number; style?: 'modern' | 'classic' | 'trap'; tempo?: number; displayName?: string; waitForCompletion?: boolean; timeout?: number; } interface InstrumentalGenerationRequest { prompt: string; duration?: number; instruments?: string[]; key?: string; tempo?: number; displayName?: string; waitForCompletion?: boolean; timeout?: number; } interface VocalsGenerationRequest { prompt: string; lyrics: string; duration?: number; displayName?: string; waitForCompletion?: boolean; timeout?: number; } interface SamplesGenerationRequest { prompt: string; sampleType?: string; tempo?: number; duration?: number; displayName?: string; waitForCompletion?: boolean; timeout?: number; } interface Audio2AudioRequest { sourceFile: File | Blob | string; prompt: string; refAudioStrength?: number; audioDuration?: number; inferStep?: number; guidanceScale?: number; displayName?: string; waitForCompletion?: boolean; timeout?: number; } interface SongBloomRequest { lyrics: string; referenceFile: File | Blob | string; duration?: number; guidanceScale?: number; numInferenceSteps?: number; seed?: number; displayName?: string; waitForCompletion?: boolean; timeout?: number; } interface RetakeRequest { originalJobId: number; retakeVariance?: number; retakeSeeds?: number[]; displayName?: string; waitForCompletion?: boolean; timeout?: number; } interface RepaintRequest { sourceJobId: number; repaintStart: number; repaintEnd: number; prompt: string; lyrics?: string; displayName?: string; waitForCompletion?: boolean; timeout?: number; } interface ExtendRequest { sourceJobId: number; leftExtendLength?: number; rightExtendLength?: number; prompt: string; lyrics?: string; extendSeeds?: number[]; displayName?: string; waitForCompletion?: boolean; timeout?: number; } interface EditRequest { sourceJobId: number; editTargetPrompt: string; editTargetLyrics?: string; editType?: 'remix' | 'only_lyrics'; editNMin?: number; editNMax?: number; editNAvg?: number; displayName?: string; waitForCompletion?: boolean; timeout?: number; } interface VoiceConversionRequest { sourceFile?: File | Blob | string; url?: string; voiceUuid: string; waitForCompletion?: boolean; timeout?: number; } interface VoiceConversionResult { job: Job; outputUrl?: string; } interface MultiVoiceSegment { text: string; voiceId: number | string; startTime?: number; endTime?: number; speakerLabel?: string; } interface MultiVoiceTTSRequest { segments: MultiVoiceSegment[]; mixMode?: 'sequential' | 'parallel' | 'timed'; outputFormat?: 'wav' | 'mp3' | 'ogg'; silenceDuration?: number; normalizeVolume?: boolean; generationParams?: Record<string, any>; waitForCompletion?: boolean; timeout?: number; } interface MultiVoiceTTSResult { job: Job; outputUrl?: string; totalDuration?: number; segmentsCount?: number; uniqueVoicesCount?: number; } interface VoiceCollectionRequest { name: string; description?: string; isPublic?: boolean; color?: string; icon?: string; voiceIds?: number[]; } interface VoiceCollectionResult { collection: VoiceCollection; message: string; } interface VoiceCollection { id: number; userId: string; name: string; description?: string; isPublic: boolean; color?: string; icon?: string; voiceCount?: number; voices?: VoiceProfile[]; createdAt: string; updatedAt: string; } interface PublicPreviewRequest { voiceIdentifier: string; inputText: string; targetLanguage?: string; } interface PublicPreviewResult { audioUrl: string; duration?: number; } /** * Voice Service * Handles voice cloning and TTS operations */ declare class VoiceService { private client; constructor(client: AudioPodClient); /** * Clone a voice from an audio file * This method first creates a voice profile, then uses it for cloning */ cloneVoice(request: VoiceCloneRequest): Promise<VoiceCloneResult>; /** * Create a reusable voice profile */ createVoiceProfile(name: string, voiceFile: File | Blob | string, description?: string, isPublic?: boolean, waitForCompletion?: boolean, timeout?: number): Promise<VoiceProfile>; /** * Generate speech using an existing voice profile */ generateSpeech(voiceId: number | string, text: string, options?: { language?: string; speed?: number; audioFormat?: 'mp3' | 'wav'; waitForCompletion?: boolean; timeout?: number; }): Promise<VoiceCloneResult>; /** * List available voice profiles */ listVoiceProfiles(options?: { voiceType?: 'custom' | 'standard'; isPublic?: boolean; includePublic?: boolean; limit?: number; skip?: number; }): Promise<VoiceProfile[]>; /** * Get details of a specific voice profile */ getVoiceProfile(voiceId: number | string): Promise<VoiceProfile>; /** * Delete a voice profile */ deleteVoiceProfile(voiceId: number | string): Promise<void>; /** * Get voice cloning job status */ getJobStatus(jobId: number): Promise<Job>; /** * List voice cloning jobs */ listCloningJobs(options?: { skip?: number; limit?: number; status?: string; }): Promise<Job[]>; /** * Stream voice generation (WebSocket connection) */ streamVoiceGeneration(voiceId: number | string, text: string, options?: { language?: string; speed?: number; onProgress?: (progress: number) => void; onAudioChunk?: (chunk: ArrayBuffer) => void; onComplete?: (result: any) => void; onError?: (error: any) => void; }): Promise<void>; /** * Convert source audio to match target voice characteristics */ convertVoice(request: VoiceConversionRequest): Promise<VoiceConversionResult>; /** * Generate multi-voice TTS with multiple speakers */ generateMultiVoiceTTS(request: MultiVoiceTTSRequest): Promise<MultiVoiceTTSResult>; /** * Create a voice collection */ createVoiceCollection(request: VoiceCollectionRequest): Promise<VoiceCollectionResult>; /** * List voice collections */ listVoiceCollections(options?: { includeVoices?: boolean; includePublic?: boolean; }): Promise<VoiceCollection[]>; /** * Update a voice collection */ updateVoiceCollection(collectionId: number, updates: Partial<VoiceCollectionRequest>): Promise<VoiceCollectionResult>; /** * Delete a voice collection */ deleteVoiceCollection(collectionId: number): Promise<void>; /** * Add voices to a collection */ addVoicesToCollection(collectionId: number, voiceIds: number[]): Promise<void>; /** * Remove voices from a collection */ removeVoicesFromCollection(collectionId: number, voiceIds: number[]): Promise<void>; /** * Generate public voice preview (no authentication required) */ generatePublicPreview(request: PublicPreviewRequest): Promise<PublicPreviewResult>; /** * Populate provider voices (admin only) */ populateProviderVoices(provider: 'openai' | 'google_gemini' | 'audiopod_sonic'): Promise<{ message: string; count: number; }>; /** * Get unified TTS job status (works for both single and multi-voice TTS) */ getUnifiedJobStatus(jobId: number): Promise<Job>; /** * Get unified TTS history (both single and multi-voice jobs) */ getUnifiedTTSHistory(options?: { limit?: number; offset?: number; status?: string; jobType?: 'single' | 'multi'; }): Promise<Job[]>; } /** * Music Service * Handles music generation operations */ declare class MusicService { private client; constructor(client: AudioPodClient); /** * Generate music from text prompt */ generateMusic(request: MusicGenerationRequest): Promise<MusicGenerationResult>; /** * Generate rap music from prompt and lyrics */ generateRap(request: RapGenerationRequest): Promise<MusicGenerationResult>; /** * Generate instrumental music from prompt */ generateInstrumental(request: InstrumentalGenerationRequest): Promise<MusicGenerationResult>; /** * Generate vocals from prompt and lyrics */ generateVocals(request: VocalsGenerationRequest): Promise<MusicGenerationResult>; /** * Generate audio samples from prompt */ generateSamples(request: SamplesGenerationRequest): Promise<MusicGenerationResult>; /** * Transform audio to audio with new characteristics */ generateAudio2Audio(request: Audio2AudioRequest): Promise<MusicGenerationResult>; /** * Generate music using SongBloom with reference audio */ generateSongBloom(request: SongBloomRequest): Promise<MusicGenerationResult>; /** * Create a retake/variation of existing music */ retakeMusic(request: RetakeRequest): Promise<MusicGenerationResult>; /** * Repaint sections of existing music */ repaintMusic(request: RepaintRequest): Promise<MusicGenerationResult>; /** * Extend existing music with additional content */ extendMusic(request: ExtendRequest): Promise<MusicGenerationResult>; /** * Edit existing music with new style or lyrics */ editMusic(request: EditRequest): Promise<MusicGenerationResult>; /** * Get music generation job status */ getJobStatus(jobId: number): Promise<Job>; /** * List music generation jobs */ listJobs(options?: { limit?: number; offset?: number; status?: string; }): Promise<Job[]>; /** * Like a music track */ likeMusicTrack(jobId: number): Promise<{ liked: boolean; totalLikes: number; }>; /** * Unlike a music track */ unlikeMusicTrack(jobId: number): Promise<{ liked: boolean; totalLikes: number; }>; /** * Share a music track */ shareMusicTrack(jobId: number, options?: { title?: string; description?: string; expirationDate?: string; }): Promise<{ shareToken: string; shareUrl: string; }>; /** * Get music track statistics */ getMusicTrackStats(jobId: number): Promise<{ likes: number; dislikes: number; shares: number; comments: number; }>; /** * Delete a music generation job */ deleteMusicJob(jobId: number): Promise<void>; /** * Get shared music track (public access) */ getSharedTrack(shareToken: string): Promise<MusicGenerationResult>; } /** * Transcription Service * Handles audio transcription operations */ declare class TranscriptionService { private client; constructor(client: AudioPodClient); /** * Transcribe audio to text */ transcribeAudio(request: TranscriptionRequest): Promise<TranscriptionResult>; /** * Transcribe from URL */ transcribeUrl(url: string, options?: { language?: string; modelType?: 'whisperx' | 'faster-whisper'; enableSpeakerDiarization?: boolean; waitForCompletion?: boolean; timeout?: number; }): Promise<TranscriptionResult>; /** * Get transcription job */ getTranscriptionJob(jobId: number): Promise<TranscriptionResult>; /** * Download transcript */ downloadTranscript(jobId: number, format?: 'json' | 'txt' | 'srt' | 'vtt' | 'pdf' | 'docx' | 'html'): Promise<string>; } declare class TranslationService { private client; constructor(client: AudioPodClient); translateAudio(request: TranslationRequest): Promise<TranslationResult>; getTranslationJob(jobId: number): Promise<TranslationResult>; listTranslationJobs(options?: { skip?: number; limit?: number; }): Promise<TranslationResult[]>; deleteTranslationJob(jobId: number): Promise<void>; } declare class CreditService { private client; constructor(client: AudioPodClient); getCreditBalance(): Promise<CreditInfo>; getUsageHistory(): Promise<CreditUsageRecord[]>; getCreditMultipliers(): Promise<Record<string, number>>; } declare class SpeakerService { private client; constructor(client: AudioPodClient); diarizeSpeakers(audioFile: File | Blob | string, numSpeakers?: number, waitForCompletion?: boolean, timeout?: number): Promise<any>; } declare class DenoiserService { private client; constructor(client: AudioPodClient); denoiseAudio(audioFile: File | Blob | string, qualityMode?: string, waitForCompletion?: boolean, timeout?: number): Promise<any>; } /** * Stem Extraction Service * Handles audio stem separation operations */ declare class StemExtractionService { private client; constructor(client: AudioPodClient); /** * Extract stems from audio (vocals, drums, bass, other instruments) */ extractStems(request: StemExtractionRequest): Promise<StemExtractionResult>; /** * Get stem extraction job status */ getJobStatus(jobId: number): Promise<StemExtractionResult>; /** * List stem extraction jobs */ listJobs(options?: { skip?: number; limit?: number; }): Promise<StemExtractionResult[]>; /** * Delete stem extraction job */ deleteJob(jobId: number): Promise<void>; } /** * AudioPod Client * Main client class for the AudioPod API */ declare class AudioPodClient { private readonly httpClient; private readonly config; readonly voice: VoiceService; readonly music: MusicService; readonly transcription: TranscriptionService; readonly translation: TranslationService; readonly credits: CreditService; readonly speaker: SpeakerService; readonly denoiser: DenoiserService; readonly stemExtraction: StemExtractionService; constructor(config: AudioPodConfig); private createHttpClient; private handleApiError; /** * Make a GET request to the API */ get<T = any>(endpoint: string, params?: Record<string, any>): Promise<T>; /** * Make a POST request to the API */ post<T = any>(endpoint: string, data?: any, config?: any): Promise<T>; /** * Make a PUT request to the API */ put<T = any>(endpoint: string, data?: any): Promise<T>; /** * Make a DELETE request to the API */ delete<T = any>(endpoint: string): Promise<T>; /** * Upload a file to the API */ uploadFile<T = any>(endpoint: string, fileData: File | Blob, formData?: Record<string, any>, onProgress?: (progress: UploadProgress) => void): Promise<T>; /** * Wait for a job to complete */ waitForJobCompletion<T = any>(jobId: number, timeout?: number, // 5 minutes pollInterval?: number, // 5 seconds onProgress?: (job: Job) => void): Promise<T>; /** * Get job status */ getJobStatus(jobId: number): Promise<Job>; /** * Cancel a job */ cancelJob(jobId: number): Promise<void>; /** * Check API health */ checkHealth(): Promise<{ status: string; timestamp: string; }>; /** * Get current user information */ getUserInfo(): Promise<any>; /** * Get API configuration */ getConfig(): Readonly<Required<AudioPodConfig>>; /** * Update API key */ updateApiKey(apiKey: string): void; /** * Set debug mode */ setDebug(enabled: boolean): void; } /** * React Hooks for AudioPod SDK * Easy-to-use React hooks for AudioPod functionality */ /** * Base AudioPod hook */ declare function useAudioPod(apiKey?: string, options?: UseAudioPodOptions): { client: AudioPodClient | null; isInitialized: boolean; error: AudioPodError | null; }; /** * Voice cloning hook */ declare function useVoiceCloning(apiKey?: string, options?: UseVoiceCloningOptions): { cloneVoice: (request: VoiceCloneRequest) => Promise<void>; cancel: () => void; isLoading: boolean; progress: number; result: VoiceCloneResult | null; error: AudioPodError | null; isInitialized: boolean; }; /** * Music generation hook */ declare function useMusicGeneration(apiKey?: string, options?: UseMusicGenerationOptions): { generateMusic: (request: MusicGenerationRequest) => Promise<void>; cancel: () => void; isLoading: boolean; progress: number; result: MusicGenerationResult | null; error: AudioPodError | null; isInitialized: boolean; }; /** * Transcription hook */ declare function useTranscription(apiKey?: string, options?: UseTranscriptionOptions): { transcribeAudio: (request: TranscriptionRequest) => Promise<void>; cancel: () => void; isLoading: boolean; progress: number; result: TranscriptionResult | null; error: AudioPodError | null; isInitialized: boolean; }; /** * Credits hook */ declare function useCredits(apiKey?: string): { credits: CreditInfo | null; isLoading: boolean; error: AudioPodError | null; refetch: () => Promise<void>; isInitialized: boolean; }; export { AudioPodClient, JobStatus, TTSProvider, VoiceType, useAudioPod, useCredits, useMusicGeneration, useTranscription, useVoiceCloning }; export type { ApiResponse, Audio2AudioRequest, AudioPodConfig, AudioPodError, AudioPodEvent, CreditInfo, CreditUsageRecord, EditRequest, ExtendRequest, InstrumentalGenerationRequest, Job, JobProgress, JobStatusEvent, MultiVoiceSegment, MultiVoiceTTSRequest, MultiVoiceTTSResult, MusicGenerationRequest, MusicGenerationResult, ProgressEvent, PublicPreviewRequest, PublicPreviewResult, RapGenerationRequest, RepaintRequest, RetakeRequest, SamplesGenerationRequest, SongBloomRequest, StemExtractionRequest, StemExtractionResult, TranscriptionRequest, TranscriptionResult, TranscriptionSegment, TranslationRequest, TranslationResult, UploadProgress, UseAudioPodOptions, UseMusicGenerationOptions, UseTranscriptionOptions, UseVoiceCloningOptions, VocalsGenerationRequest, VoiceCloneRequest, VoiceCloneResult, VoiceCollection, VoiceCollectionRequest, VoiceCollectionResult, VoiceConversionRequest, VoiceConversionResult, VoiceProfile };