Hello AI devs
Iβm excited to introduce Flame Audio AI, an open-source, full-stack voice platform built on Google Generative AI that offers:
Speech-to-Text
Text-to-Speech
Speaker Diarization
Multi-language support (50+ languages)
Audio format support: MP3, WAV, M4A & more
Responsive UI with light/dark themes
Quick Installation
git clone GitHub - Bag-zy/flame-audio
cd flame-audio
npm install
npm run dev
Visit localhost:3000 to access the live demo.
Donβt forget to add a .env.local (MongoDB URI, NextAuth secret, Google AI API key) as described in the README.
Tech Stack
Next.js 15 β frontend & API
React & TypeScript
Tailwind CSS, Radix UI, Lucide React Icons
NextAuth.js + MongoDB/Mongoose
Powered by Google Generative AI
How You Can Help
Test & report issues
Suggest new features or languages
Give feedback on UX/UI
Share ideas for enhancements
Iβd love the community to:
-
Try the install and demo
-
Share your experiences or questions here
-
Discuss any improvements or integrations youβd love to see
Repo & live demo: GitHub - Bag-zy/flame-audio
Thanks for checking it out β looking forward to your feedback and collaboration!