elevenlabs-reference-architecture

# ElevenLabs Reference Architecture ## Overview Production-ready architecture for ElevenLabs TTS/voice applications. Covers project layout, service layers, caching, streaming, and multi-model orchestration. ## Prerequisites - Understanding of layered architecture patterns - ElevenLabs SDK knowledge (see `elevenlabs-sdk-patterns`) - TypeScript project with async patterns - Redis (optional, for distributed caching) ## Instructions ### Step 1: Project Structure ``` my-elevenlabs-service/ ├── src/ │ ├── elevenlabs/ │ │ ├── client.ts # Singleton client with retry config │ │ ├── config.ts # Environment-aware configuration │ │ ├── models.ts # Model selection logic │ │ ├── errors.ts # Error classification (see sdk-patterns) │ │ └── types.ts # TypeScript interfaces │ ├── services/ │ │ ├── tts-service.ts # Text-to-Speech orchestration │ │ ├── voice-service.ts # Voice management (clone, list, settings) │ │ ├── audio-service.ts # SFX, isolation, transcription │ │ └── cache-service.ts # Audio caching layer │ ├── api/ │ │ ├── routes/ │ │ │ ├── tts.ts # POST /api/tts │ │ │ ├── voices.ts # GET/POST /api/voices │ │ │ ├── webhooks.ts # POST /webhooks/elevenlabs │ │ │ └── health.ts # GET /health │ │ └── middleware/ │ │ ├── rate-limit.ts # Request throttling │ │ └── auth.ts # Your app's ...