- Implementation of Bridge's key features using
- Google Gemini Pro
- Google Cloud Natural Language
- Google Cloud TTS
- LLM model of Google AI studio
- Google Gemini Pro
- Build with FastAPI
- Gemini Pro: High-level human language understanding and communication abilities
- Flutter Real-time STT: Supports real-time voice data input
- Google Place API: Identifies user location information
- Google Cloud Translation: Supports 134 languages
- Google Cloud TTS: Provides real-time language-specific responses
- Flutter: Supports various platforms
- Docker-based GPU Server: Provides fast and stable service
- Customized User Settings: Provides a personalized communication environment tailored to the user's needs
- Data Analysis: Analyzes user patterns and improves model performance
- Supports Real-time Context-based Communication: Provides responses considering user location, voice input, and intent
- Multilingual Support: Expands global user accessibility with support for 134 languages
- Personalized Settings: Offers a communication environment tailored to the user's needs
- Data-driven Model Improvement: Enhances recommendation system performance through continuous data analysis
import google.generativeai as genai
from google.cloud import speech
from google.cloud import texttospeech
from gtts import gTTS
import os
import argparse
import json
import datetime
import time
python 3.8x (at least)
cd bridge_AI
python -m venv (venv)
(venv)\Scripts\activate
pip install -r requirements.txt
cd app
uvicorn main:app --reload --host=0.0.0.0 --port=5000
- DL Flow : Input(Question Audio Data) → Output(Recommendation Audio Data from Gemini pro)