🧠🎙️ Speech Transcriber & Synthesizer App

A Dockerized web app for transcribing speech to text and synthesizing multilingual speech responses. (Python + Flutter)

---

🚀 Features

• 🎧 Speech-to-Text using Whisper
• 🔊 Text-to-Speech with Coqui TTS
• 🌍 Supports multiple languages
• 💻 Frontend UI built with Flutter Web
• 🐳 Seamless deployment using docker-compose
• 🔁 Configurable ports, IPs, and runtime behavior

---

📦 Tech Stack

• Backend: Python, Sanic, Whisper, Coqui TTS
• Frontend: Flutter (Web)
• Containerization: Docker, Docker Compose
• Web Server: Nginx (templated via nginx.conf.template)

---

🧪 Getting Started

🔧 Prerequisites

• Git
• Docker
• Docker Compose

🏗️ Clone, Build and Run

git clone https://github.com/PhillMckinnon/Flutter_Python_Speech_App
cd Flutter_Python_Speech_App
docker-compose build
docker-compose up

Once running:

• Backend API: http://localhost:5000
• Frontend UI: http://localhost:8080

---

⚙️ Configuration

You can customize the behavior and ports by editing:

• 📄 .env – backend environment variables (e.g., model settings)
• 📄 docker-compose.yaml – adjust exposed ports or volumes
• 📄 nginx.conf.template – update fallback rules or paths
• 📄 entrypoint.sh – modify frontend routing or fallback logic

---

📫 Contact

Have questions, ideas, or feedback?

• ✉️ Email: phillipmckinnonwork@proton.me
• 💻 GitHub: @PhillMckinnon

---

📝 License

This project is licensed under the MIT License.