https://github.com/albertov5/va-gpt

CLI Voice Assistant GPT (pgvector, AWS polly, whisper)
https://github.com/albertov5/va-gpt

cli embeddings pgvector python speech-recognition

Last synced: 6 months ago
JSON representation

CLI Voice Assistant GPT (pgvector, AWS polly, whisper)

• Host: GitHub
• URL: https://github.com/albertov5/va-gpt
• Owner: AlbertoV5
• License: mit
• Created: 2023-06-12T01:31:09.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2023-06-12T01:37:21.000Z (about 3 years ago)
• Last Synced: 2023-10-08T22:23:52.827Z (almost 3 years ago)
• Topics: cli, embeddings, pgvector, python, speech-recognition
• Language: Python
• Homepage:
• Size: 471 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# GPT Voice Assistant

Interact with GPT via voice as a CLI tool. Context aware assistant via pgvector and text embeddings.

## Assistant Layer

OpenAI's Chat Completion API for text and AWS Polly API for speech synthesis.

## Storage Layer

PostgreSQL support for storing chat interactions as messages with embeddings. Options to store audio files.

## Audio Layer

Uses PyAudio for buffer reading and PyTorch for loading data into Whisper. Uses ffmpeg for playback.

## Example

![GPTVA](./.github/gptva.png)