@happyvertical/smrt-voice 0.51.32 → 0.51.34

package/dist/voice-profile.d.ts

@@ -0,0 +1,203 @@
+/**
+ * Voice Profile Model
+ *
+ * Manages voice profiles for AI-powered voice synthesis and cloning.
+ * Supports voice design via natural language descriptions and voice
+ * cloning from audio samples.
+ */
+import type { SmrtObjectOptions } from '@happyvertical/smrt-core';
+import { SmrtObject } from '@happyvertical/smrt-core';
+import type { SpeechVoice } from '@happyvertical/speech';
+/**
+ * Voice profile status
+ */
+export type VoiceProfileStatus = 'pending' | 'processing' | 'ready' | 'failed';
+/**
+ * Voice gender classification
+ */
+export type VoiceGender = 'male' | 'female' | 'neutral';
+/**
+ * Voice profile creation options
+ */
+export interface VoiceProfileOptions extends SmrtObjectOptions {
+    /**
+     * Human-readable name for the voice profile
+     */
+    name?: string;
+    /**
+     * Description of the voice characteristics
+     */
+    description?: string | null;
+    /**
+     * ISO language code (e.g., 'en-US', 'zh-CN')
+     */
+    language?: string;
+    /**
+     * Voice gender classification
+     * @default 'neutral'
+     */
+    gender?: VoiceGender;
+    /**
+     * Natural language description for voice design
+     * Used when creating a voice from scratch
+     */
+    designPrompt?: string | null;
+    /**
+     * Asset ID of the audio sample for voice cloning
+     * Should be at least 3 seconds of clear speech
+     */
+    sampleAssetId?: string | null;
+    /**
+     * Provider-specific voice data (ID, embedding, etc.)
+     * Stored after voice creation/cloning
+     */
+    voiceData?: Record<string, unknown> | null;
+    /**
+     * Default speech speed multiplier
+     * @default 1.0
+     */
+    defaultSpeed?: number;
+    /**
+     * Default pitch adjustment in semitones
+     * @default 0
+     */
+    defaultPitch?: number;
+    /**
+     * Voice profile status
+     * @default 'pending'
+     */
+    status?: VoiceProfileStatus;
+    /**
+     * TTS provider that created this voice
+     * @default 'qwen3-tts'
+     */
+    provider?: string;
+    /**
+     * Error message if status is 'failed'
+     */
+    errorMessage?: string | null;
+    /**
+     * Tenant ID for multi-tenant isolation
+     * Null for global/default voices
+     */
+    tenantId?: string | null;
+}
+/**
+ * Voice profile for AI-powered speech synthesis
+ *
+ * VoiceProfile represents a configured voice identity that can be used
+ * for text-to-speech synthesis. Voices can be created through:
+ * - Voice design: Natural language description of desired voice characteristics
+ * - Voice cloning: 3+ second audio sample for voice replication
+ *
+ * @example
+ * ```typescript
+ * import { VoiceProfile } from '@happyvertical/smrt-voice';
+ *
+ * // Create a designed voice
+ * const anchorVoice = new VoiceProfile({
+ *   name: 'News Anchor',
+ *   description: 'Professional news anchor voice with clear enunciation',
+ *   language: 'en-US',
+ *   gender: 'male',
+ *   designPrompt: 'Warm, authoritative male voice with slight gravitas, suitable for news broadcasts',
+ *   provider: 'qwen3-tts',
+ * });
+ *
+ * // Create a cloned voice
+ * const clonedVoice = new VoiceProfile({
+ *   name: 'Custom Voice',
+ *   description: 'Cloned from user sample',
+ *   language: 'en-US',
+ *   sampleAssetId: 'asset-123',
+ *   provider: 'qwen3-tts',
+ * });
+ * ```
+ */
+export declare class VoiceProfile extends SmrtObject {
+    /**
+     * Tenant ID for multi-tenant isolation
+     * Nullable to support global/default voices
+     */
+    tenantId: string | null;
+    /**
+     * Human-readable name for the voice profile
+     */
+    name: string;
+    /**
+     * Description of the voice characteristics
+     */
+    description: string | null;
+    /**
+     * ISO language code (e.g., 'en-US', 'zh-CN')
+     */
+    language: string;
+    /**
+     * Voice gender classification
+     */
+    gender: VoiceGender;
+    /**
+     * Natural language description for voice design
+     * Used when creating a voice from scratch via AI
+     */
+    designPrompt: string | null;
+    /**
+     * Asset ID of the audio sample for voice cloning
+     * Should be at least 3 seconds of clear speech
+     */
+    sampleAssetId: string | null;
+    /**
+     * Provider-specific voice data (ID, embedding, etc.)
+     * Stored after voice creation/cloning is complete
+     */
+    voiceData: Record<string, unknown> | null;
+    /**
+     * Default speech speed multiplier (0.5 - 2.0)
+     * 1.0 = normal speed
+     */
+    defaultSpeed: number;
+    /**
+     * Default pitch adjustment in semitones (-20 to 20)
+     * 0 = no adjustment
+     */
+    defaultPitch: number;
+    /**
+     * Voice profile status
+     * - pending: Profile created but voice not yet generated
+     * - processing: Voice generation/cloning in progress
+     * - ready: Voice is ready for use
+     * - failed: Voice generation failed
+     */
+    status: VoiceProfileStatus;
+    /**
+     * TTS provider that created/manages this voice
+     */
+    provider: string;
+    /**
+     * Error message if status is 'failed'
+     */
+    errorMessage: string | null;
+    constructor(options?: VoiceProfileOptions);
+    /**
+     * Check if this voice profile uses voice cloning
+     */
+    get isCloned(): boolean;
+    /**
+     * Check if this voice profile uses voice design
+     */
+    get isDesigned(): boolean;
+    /**
+     * Check if the voice is ready for use
+     */
+    get isReady(): boolean;
+    /**
+     * Check if this is a global (default) voice
+     */
+    get isGlobal(): boolean;
+    /**
+     * Convert this persisted profile into the runtime voice shape consumed by
+     * @happyvertical/speech adapters.
+     */
+    toSpeechVoice(): SpeechVoice;
+}
+//# sourceMappingURL=voice-profile.d.ts.map

package/dist/voice-profile.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"voice-profile.d.ts","sourceRoot":"","sources":["../src/voice-profile.ts"],"names":[],"mappings":"AAAA;;;;;;GAMG;AAEH,OAAO,KAAK,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAC;AAClE,OAAO,EAAmB,UAAU,EAAQ,MAAM,0BAA0B,CAAC;AAE7E,OAAO,KAAK,EAAE,WAAW,EAAE,MAAM,uBAAuB,CAAC;AAEzD;;GAEG;AACH,MAAM,MAAM,kBAAkB,GAAG,SAAS,GAAG,YAAY,GAAG,OAAO,GAAG,QAAQ,CAAC;AAE/E;;GAEG;AACH,MAAM,MAAM,WAAW,GAAG,MAAM,GAAG,QAAQ,GAAG,SAAS,CAAC;AAExD;;GAEG;AACH,MAAM,WAAW,mBAAoB,SAAQ,iBAAiB;IAC5D;;OAEG;IACH,IAAI,CAAC,EAAE,MAAM,CAAC;IAEd;;OAEG;IACH,WAAW,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAE5B;;OAEG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAC;IAElB;;;OAGG;IACH,MAAM,CAAC,EAAE,WAAW,CAAC;IAErB;;;OAGG;IACH,YAAY,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAE7B;;;OAGG;IACH,aAAa,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAE9B;;;OAGG;IACH,SAAS,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,IAAI,CAAC;IAE3C;;;OAGG;IACH,YAAY,CAAC,EAAE,MAAM,CAAC;IAEtB;;;OAGG;IACH,YAAY,CAAC,EAAE,MAAM,CAAC;IAEtB;;;OAGG;IACH,MAAM,CAAC,EAAE,kBAAkB,CAAC;IAE5B;;;OAGG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAC;IAElB;;OAEG;IACH,YAAY,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAE7B;;;OAGG;IACH,QAAQ,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CAC1B;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA+BG;AACH,qBAWa,YAAa,SAAQ,UAAU;IAC1C;;;OAGG;IAEH,QAAQ,EAAE,MAAM,GAAG,IAAI,CAAQ;IAE/B;;OAEG;IACH,IAAI,EAAE,MAAM,CAAM;IAElB;;OAEG;IACH,WAAW,EAAE,MAAM,GAAG,IAAI,CAAQ;IAElC;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAW;IAE3B;;OAEG;IACH,MAAM,EAAE,WAAW,CAAa;IAEhC;;;OAGG;IACH,YAAY,EAAE,MAAM,GAAG,IAAI,CAAQ;IAEnC;;;OAGG;IAEH,aAAa,EAAE,MAAM,GAAG,IAAI,CAAQ;IAEpC;;;OAGG;IACH,SAAS,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,IAAI,CAAQ;IAEjD;;;OAGG;IACH,YAAY,EAAE,MAAM,CAAO;IAE3B;;;OAGG;IACH,YAAY,EAAE,MAAM,CAAK;IAEzB;;;;;;OAMG;IACH,MAAM,EAAE,kBAAkB,CAAa;IAEvC;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAe;IAE/B;;OAEG;IACH,YAAY,EAAE,MAAM,GAAG,IAAI,CAAQ;gBAEvB,OAAO,GAAE,mBAAwB;IAwB7C;;OAEG;IACH,IAAI,QAAQ,IAAI,OAAO,CAEtB;IAED;;OAEG;IACH,IAAI,UAAU,IAAI,OAAO,CAExB;IAED;;OAEG;IACH,IAAI,OAAO,IAAI,OAAO,CAErB;IAED;;OAEG;IACH,IAAI,QAAQ,IAAI,OAAO,CAEtB;IAED;;;OAGG;IACH,aAAa,IAAI,WAAW;CA0B7B"}

package/dist/voice-sample.d.ts

@@ -0,0 +1,146 @@
+/**
+ * Voice Sample Model
+ *
+ * Manages audio samples used for voice cloning.
+ * Samples should be at least 3 seconds of clear speech.
+ */
+import type { SmrtObjectOptions } from '@happyvertical/smrt-core';
+import { SmrtObject } from '@happyvertical/smrt-core';
+/**
+ * Audio sample quality rating
+ */
+export type SampleQuality = 'low' | 'medium' | 'high';
+/**
+ * Voice sample creation options
+ */
+export interface VoiceSampleOptions extends SmrtObjectOptions {
+    /**
+     * Voice profile this sample belongs to
+     */
+    voiceProfileId?: string | null;
+    /**
+     * Asset ID of the audio file
+     */
+    assetId?: string | null;
+    /**
+     * Sample duration in seconds
+     */
+    duration?: number;
+    /**
+     * Transcription of what was said in the sample
+     */
+    transcription?: string | null;
+    /**
+     * Quality rating based on audio analysis
+     * @default 'medium'
+     */
+    quality?: SampleQuality;
+    /**
+     * Sample rate in Hz (e.g., 44100, 48000)
+     */
+    sampleRate?: number | null;
+    /**
+     * Number of audio channels (1 = mono, 2 = stereo)
+     */
+    channels?: number | null;
+    /**
+     * Audio format (e.g., 'wav', 'mp3', 'ogg')
+     */
+    format?: string | null;
+    /**
+     * Whether this is the primary sample for the voice profile
+     * @default false
+     */
+    isPrimary?: boolean;
+    /**
+     * Tenant ID for multi-tenant isolation
+     */
+    tenantId?: string | null;
+}
+/**
+ * Audio sample for voice cloning
+ *
+ * VoiceSample represents an audio recording used as source material
+ * for voice cloning. For best results, samples should be:
+ * - At least 3 seconds long
+ * - Clear speech without background noise
+ * - Single speaker only
+ * - High quality (44.1kHz or higher)
+ *
+ * Multiple samples can be associated with a single VoiceProfile
+ * to improve voice cloning quality.
+ *
+ * @example
+ * ```typescript
+ * import { VoiceSample } from '@happyvertical/smrt-voice';
+ *
+ * const sample = new VoiceSample({
+ *   voiceProfileId: 'voice-123',
+ *   assetId: 'asset-456',
+ *   duration: 5.2,
+ *   transcription: 'Hello, this is a test recording for voice cloning.',
+ *   quality: 'high',
+ *   sampleRate: 48000,
+ *   channels: 1,
+ *   format: 'wav',
+ *   isPrimary: true,
+ * });
+ * ```
+ */
+export declare class VoiceSample extends SmrtObject {
+    /**
+     * Tenant ID for multi-tenant isolation
+     */
+    tenantId: string | null;
+    /**
+     * Voice profile this sample belongs to
+     */
+    voiceProfileId: string | null;
+    /**
+     * Asset ID of the audio file
+     * References an Asset in smrt-assets
+     */
+    assetId: string | null;
+    /**
+     * Sample duration in seconds
+     */
+    duration: number;
+    /**
+     * Transcription of what was said in the sample
+     * Used for alignment and quality verification
+     */
+    transcription: string | null;
+    /**
+     * Quality rating based on audio analysis
+     * - low: Noisy or short samples
+     * - medium: Acceptable quality
+     * - high: Clear audio, good length
+     */
+    quality: SampleQuality;
+    /**
+     * Sample rate in Hz
+     */
+    sampleRate: number | null;
+    /**
+     * Number of audio channels
+     */
+    channels: number | null;
+    /**
+     * Audio format
+     */
+    format: string | null;
+    /**
+     * Whether this is the primary sample for the voice profile
+     */
+    isPrimary: boolean;
+    constructor(options?: VoiceSampleOptions);
+    /**
+     * Check if sample meets minimum duration requirement (3 seconds)
+     */
+    get meetsMinDuration(): boolean;
+    /**
+     * Check if sample is high quality and suitable for cloning
+     */
+    get isSuitableForCloning(): boolean;
+}
+//# sourceMappingURL=voice-sample.d.ts.map

package/dist/voice-sample.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"voice-sample.d.ts","sourceRoot":"","sources":["../src/voice-sample.ts"],"names":[],"mappings":"AAAA;;;;;GAKG;AAEH,OAAO,KAAK,EAAE,iBAAiB,EAAE,MAAM,0BAA0B,CAAC;AAClE,OAAO,EAGL,UAAU,EAEX,MAAM,0BAA0B,CAAC;AAIlC;;GAEG;AACH,MAAM,MAAM,aAAa,GAAG,KAAK,GAAG,QAAQ,GAAG,MAAM,CAAC;AAEtD;;GAEG;AACH,MAAM,WAAW,kBAAmB,SAAQ,iBAAiB;IAC3D;;OAEG;IACH,cAAc,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAE/B;;OAEG;IACH,OAAO,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAExB;;OAEG;IACH,QAAQ,CAAC,EAAE,MAAM,CAAC;IAElB;;OAEG;IACH,aAAa,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAE9B;;;OAGG;IACH,OAAO,CAAC,EAAE,aAAa,CAAC;IAExB;;OAEG;IACH,UAAU,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAE3B;;OAEG;IACH,QAAQ,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAEzB;;OAEG;IACH,MAAM,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;IAEvB;;;OAGG;IACH,SAAS,CAAC,EAAE,OAAO,CAAC;IAEpB;;OAEG;IACH,QAAQ,CAAC,EAAE,MAAM,GAAG,IAAI,CAAC;CAC1B;AAED;;;;;;;;;;;;;;;;;;;;;;;;;;;;;GA6BG;AACH,qBAWa,WAAY,SAAQ,UAAU;IACzC;;OAEG;IAEH,QAAQ,EAAE,MAAM,GAAG,IAAI,CAAQ;IAE/B;;OAEG;IAEH,cAAc,EAAE,MAAM,GAAG,IAAI,CAAQ;IAErC;;;OAGG;IAEH,OAAO,EAAE,MAAM,GAAG,IAAI,CAAQ;IAE9B;;OAEG;IACH,QAAQ,EAAE,MAAM,CAAK;IAErB;;;OAGG;IACH,aAAa,EAAE,MAAM,GAAG,IAAI,CAAQ;IAEpC;;;;;OAKG;IACH,OAAO,EAAE,aAAa,CAAY;IAElC;;OAEG;IACH,UAAU,EAAE,MAAM,GAAG,IAAI,CAAQ;IAEjC;;OAEG;IACH,QAAQ,EAAE,MAAM,GAAG,IAAI,CAAQ;IAE/B;;OAEG;IACH,MAAM,EAAE,MAAM,GAAG,IAAI,CAAQ;IAE7B;;OAEG;IACH,SAAS,EAAE,OAAO,CAAS;gBAEf,OAAO,GAAE,kBAAuB;IAiB5C;;OAEG;IACH,IAAI,gBAAgB,IAAI,OAAO,CAE9B;IAED;;OAEG;IACH,IAAI,oBAAoB,IAAI,OAAO,CAElC;CACF"}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@happyvertical/smrt-voice",
-  "version": "0.51.32",
+  "version": "0.51.34",
   "type": "module",
   "description": "Voice profile management for AI-powered voice synthesis and cloning in the SMRT ecosystem",
   "author": "HappyVertical",
@@ -29,20 +29,20 @@
     "AGENTS.md"
   ],
   "dependencies": {
-    "@happyvertical/smrt-assets": "0.51.32",
-    "@happyvertical/smrt-config": "0.51.32",
-    "@happyvertical/smrt-content": "0.51.32",
-    "@happyvertical/smrt-core": "0.51.32",
-    "@happyvertical/smrt-tenancy": "0.51.32",
+    "@happyvertical/smrt-assets": "0.51.34",
+    "@happyvertical/smrt-config": "0.51.34",
+    "@happyvertical/smrt-content": "0.51.34",
+    "@happyvertical/smrt-core": "0.51.34",
+    "@happyvertical/smrt-tenancy": "0.51.34",
     "@happyvertical/speech": "^0.94.1",
     "@happyvertical/utils": "^0.94.1"
   },
   "devDependencies": {
     "@happyvertical/logger": "^0.94.1",
-    "@happyvertical/smrt-vitest": "0.51.32",
+    "@happyvertical/smrt-vitest": "0.51.34",
     "@happyvertical/sql": "^0.94.1",
     "@types/node": "24.13.6",
-    "typescript": "5.9.3",
+    "typescript": "6.0.3",
     "vite": "8.1.4",
     "vitest": "4.1.10"
   },