Sathvik VK

GitHub archive, repository 24 of 66

hope

Python voice-agent script: Whisper speech-to-text, Gemini response, gTTS speech output, interactions logged to MongoDB.

What this is
Experiment. A small exploration of a tool, model or library.
Category
Voice
Main language
Python
Created
14 May 2025
Last pushed
14 May 2025

Description on GitHub

Voice Agent Project : This project implements a voice agent that can: 1. Convert speech to text using Whisper 2. Generate responses using Google's Gemini LLM 3. Convert text responses to speech using gTTS 4. Store all interactions in MongoDB

Found in the code

PythonOpenAI WhisperGeminigTTSMongoDB

Iterations of the same idea

More in Voice

Next repository in the archiveOr press the right arrow keybolt-flny-appBolt-generated Expo Router app shell for 'FLNY' fashion: tab screens (explore, brands, post, profile) filled with dummy data and images.

This page is generated from public GitHub metadata plus a short note I wrote after reviewing the repository. Back to the full archive