Spaces:
Sleeping
Sleeping
File size: 2,322 Bytes
6b17775 57bb9a0 e355f70 6512a89 b06881a 6512a89 b06881a 6512a89 b06881a e355f70 b06881a e355f70 b06881a e355f70 b06881a e355f70 b06881a e355f70 b06881a 6512a89 b06881a e355f70 b06881a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
import gradio as gr
from google.generativeai import GenerativeModel, configure
from gtts import gTTS
import speech_recognition as sr
import os
import tempfile
# ✅ Load API key from environment variable
GOOGLE_API_KEY = os.getenv("GEMINI_API_KEY")
if not GOOGLE_API_KEY:
raise ValueError("❌ Missing API Key! Please set GEMINI_API_KEY as an environment variable.")
# ✅ Configure Gemini securely
configure(api_key=GOOGLE_API_KEY)
gemini_model = GenerativeModel("models/gemini-1.5-flash")
def transcribe_audio(audio_path):
recognizer = sr.Recognizer()
with sr.AudioFile(audio_path) as source:
audio = recognizer.record(source)
try:
return recognizer.recognize_google(audio, language='en-US')
except sr.UnknownValueError:
return "❌ Could not understand the audio."
except sr.RequestError:
return "❌ Could not connect to Google Speech API."
def get_gemini_response(query):
try:
# Request Gemini model to answer in English
response = gemini_model.generate_content(f"Answer in English: {query}")
return response.text.replace('*', '')
except Exception as e:
return f"❌ Error from Gemini: {str(e)}"
def text_to_speech(text, lang='en'):
tts = gTTS(text=text, lang=lang)
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix=".mp3")
tts.save(temp_file.name)
return temp_file.name
# ---------------------------
# Combined function to handle voice query
# ---------------------------
def handle_voice_query(audio_file):
query = transcribe_audio(audio_file)
response = get_gemini_response(query)
audio_path = text_to_speech(response)
return query, response, audio_path
with gr.Blocks() as demo:
gr.Markdown("# 🗣️ **Ask by Voice**")
gr.Markdown("### Speak your question aloud (in English)")
audio_input = gr.Audio(type="filepath", label="🎤 Speak your question")
query_text = gr.Textbox(label="🔍 Spoken Question")
gemini_response = gr.Textbox(label="📜 Gemini Response")
audio_output = gr.Audio(label="🔊 Voice Response")
submit_btn = gr.Button("➡️ Get Answer")
submit_btn.click(fn=handle_voice_query,
inputs=[audio_input],
outputs=[query_text, gemini_response, audio_output])
demo.launch()
|