A full-stack Neural Voice Synthesizer & Translator that converts text into multiple languages simultaneously and generates high-quality speech using ElevenLabs.
Home Page
11LabsM is a powerful tool designed for content creators and developers who need to localize speech content quickly. By leveraging the ElevenLabs API and advanced translation providers (DeepL, Google, MyMemory), it can take a single input text and produce high-quality audio in dozens of languages at once.
The application features a modern distributed architecture with a React frontend, a FastAPI backend, and Celery workers for asynchronous processing. It employs a content-addressed caching system in Redis to minimize API costs and latency for repeat requests.
- 🌍 Multilingual Translation - Translate text into 17+ languages simultaneously including Spanish, French, German, and more.
- 🎙️ Neural TTS Synthesis - Generate ultra-realistic speech using ElevenLabs' industry-leading neural voices.
- ⚡ Asynchronous Processing - Long-running tasks are handled in the background with Celery and Redis.
- 📊 Real-time Status Tracking - Monitor the progress of each language's translation and synthesis in real-time.
- 💾 Smart Caching - SHA-256 content-addressed caching stores generated audio to reduce costs and latency.
- 🎧 Audio Player & Downloads - Stream generated audio directly in the browser or download a ZIP of all files.
- 🛠️ Customizable Formats - Support for multiple audio formats (MP3, PCM) and bitrates.
| Layer | Technology |
|---|---|
| Frontend Framework | React 18 |
| Build Tool | Vite 5 |
| UI Components | Ant Design 6 |
| API Backend | FastAPI 0.111 |
| Task Queue | Celery 5.3 |
| Relational Database | PostgreSQL 16 |
| Cache / Broker | Redis 7.0 |
| Object Storage | MinIO / AWS S3 |
| Language | TypeScript / Python 3.10+ |
| Deployment | Vercel / Render |
- Node.js v18 or higher
- Python 3.10 or higher
- pnpm (preferred) or npm
- Docker & Docker Compose (for local development)
- ElevenLabs API Key
- DeepL or Google Translate API Key
git clone <your-repo-url>
cd 11labsMcd tts_backend
cp .env.example .env
# Edit .env and fill in your API keysThe easiest way to get started is using Docker Compose, which spins up the API, Worker, Redis, PostgreSQL, and MinIO.
# From the root directory
docker-compose -f tts_backend/docker-compose.yml up --build- Frontend:
http://localhost:5173 - Backend API:
http://localhost:8000 - API Docs:
http://localhost:8000/docs - MinIO Console:
http://localhost:9001(minioadmin / minioadmin)
| Command | Description |
|---|---|
pnpm dev |
Starts the Vite development server |
pnpm build |
Builds the application for production |
pnpm preview |
Previews the production build locally |
| Command | Description |
|---|---|
uvicorn app.main:app --reload |
Starts the FastAPI server |
celery -A app.workers.celery_app worker --loglevel=info |
Starts the Celery worker |
11labsM/
├── frontend/ # React + Vite application
│ ├── src/
│ │ ├── api/ # API client and typed fetch wrappers
│ │ ├── components/ # UI components (JobForm, JobStatus)
│ │ └── types/ # TypeScript interfaces
│ └── public/ # Static assets & Images
├── tts_backend/ # FastAPI + Celery backend
│ ├── app/
│ │ ├── api/ # API routers (jobs, voices, models)
│ │ ├── models/ # SQLAlchemy & Pydantic models
│ │ ├── services/ # TTS and Translation logic
│ │ ├── storage/ # S3 / MinIO storage logic
│ │ ├── utils/ # Redis caching and DB utils
│ │ └── workers/ # Celery task definitions
│ ├── alembic/ # Database migrations
│ └── Dockerfile # Backend container definition
├── render.yaml # Render deployment configuration
├── docker-compose.yml # Local development orchestration (links to backend)
└── PROJECT_ANALYSIS.md # Technical architecture documentation
- GitHub: github.com/PramudithaN
- LinkedIn: linkedin.com/in/pramuditha-nadun-612b1b204
- Email: pramudithanadun@gmail.com
Developed with ❤️ by Pramuditha Nadun.