VoiceGenie transforms text-based AI interactions into natural conversations. It uses Google's Gemini 1.5 Flash model to generate intelligent answers and ElevenLabs' API to vocalize them in realistic human speech.

Note to Judges: Due to ElevenLabs' strict IP filtering on shared cloud hosting (Streamlit Cloud), the hosted demo link may show an 'Unusual Activity' error. Please view the Demo Video to see the application running fully functional in a local environment.

Built With

  • eleven-labs
  • google-gemini
  • python
  • streamlit
Share this project:

Updates