Sign up to save tools and stay up to date with the latest in AI
bg
bg
1

GitHub - AlexandreSajus/JARVIS: Your own personal voice assistant: Voice to Text to LLM to Speech, displayed in a web interface

Dec 18, 2023 - github.com
The article introduces JARVIS, a personal voice assistant that uses a web interface to interact with users. The system works by converting user voice input into text using Deepgram, which is then processed by OpenAI's GPT-3 API to generate a response. This response is converted back into speech using ElevenLabs and played using Pygame. The entire conversation is displayed on a webpage using Taipy.

To install JARVIS, users need to clone the repository, install the requirements, and create a .env file with API keys for Deepgram, OpenAI, and Elevenlabs. To use JARVIS, users need to run `display.py` to start the web interface and `jarvis.py` to start the voice assistant. The system will indicate when it is listening, processing a request, and speaking the response. The response is also displayed on the web interface.

Key takeaways:

  • JARVIS is a voice personal assistant that uses a combination of Deepgram, OpenAI's GPT-3 API, and ElevenLabs to convert voice to text, generate a response, and convert the response back to speech.
  • The conversation between the user and JARVIS is displayed on a web interface, which is run by a Python script.
  • To install JARVIS, you need to clone the repository, install the requirements, and create a .env file with your API keys for Deepgram, OpenAI, and Elevenlabs.
  • To use JARVIS, you need to run two Python scripts in separate terminals. Once the scripts are running, you can start speaking into the microphone and JARVIS will process your request and respond.
View Full Article

Comments (0)

Be the first to comment!