--- title: EG Autonomous TTS Studio emoji: "🎙️" colorFrom: blue colorTo: indigo sdk: docker app_port: 7860 pinned: false license: mit short_description: Enterprise text-to-speech studio with Edge neural voices. --- # EG Autonomous TTS Studio Production-ready Text-to-Speech Space powered by FastAPI, with a branded web interface and dual synthesis modes: - `translate`: fast Google Translate TTS URL generation + proxy playback - `edge`: high-quality MP3 generation via Microsoft Edge TTS voices ## Features - Professional EG AUTONOMOUS branded UI - Instant audio playback in-browser - Language and provider switching - Voice catalog loading for Edge TTS - Long-text chunking for Translate TTS - JSON API output for direct app integration ## Project Structure - `app.py`: FastAPI application entrypoint - `tts_engine.py`: Edge TTS engine helpers and CLI utilities - `templates/index.html`: UI template - `static/app.css`: branded styles - `static/app.js`: frontend logic and API integration - `Dockerfile`: Space runtime configuration - `requirements.txt`: Python dependencies ## API Endpoints ### Health `GET /health` ### Bootstrap data `GET /api/bootstrap` Returns defaults, providers, and network information for the UI. ### Translate URL `GET /api/translate-url?text=Hello&tl=en` Returns: - `directUrl` - `proxyUrl` - `segments` ### Translate audio proxy `GET /api/translate-audio?text=Hello&tl=en` Returns playable audio bytes for embedding in `