README.md

metadata

title: S2S Voice Lab
emoji: 🎙️
colorFrom: indigo
colorTo: blue
sdk: docker
pinned: false

Voice Lab - Speech-to-Speech & Neural TTS

Advanced AI-powered Text-to-Speech and zero-shot Voice Cloning. This space runs a FastAPI backend serving a premium HTML5/JS frontend, all containerized via Docker.

Setup

Ensure you have the following secrets configured in your Space settings:

• MONGODB_URI: Connection string for user data and stats.
• HF_TOKEN: API token for Hugging Face inference models.
• JWT_SECRET: Secure string for authentication.

Tech Stack

• Backend: FastAPI (Python)
• Frontend: Vanilla JS, HTML5, CSS3 (Premium UI)
• Infrastructure: Docker on Hugging Face Spaces
• Audio: FFmpeg, Pydub