File size: 2,411 Bytes
fe12fb0 |
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 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 |
# Install the necessary libraries
!pip install google-generativeai requests gradio
import os
import requests
import google.generativeai as genai
import gradio as gr
# Configure your Google Generative AI API key
genai.configure(api_key="AIzaSyDFjkgDAcnSAXDpsQJAMOaNCKY_SNJ-sD4")
# Create the model
generation_config = {
"temperature": 1,
"top_p": 0.95,
"top_k": 64,
"max_output_tokens": 8192,
"response_mime_type": "text/plain",
}
model = genai.GenerativeModel(
model_name="gemini-1.5-pro",
generation_config=generation_config,
system_instruction="You are a human, living on Earth. You speak friendly and use casual language. You never say you're an AI or program. Your name is Ath, and you always speak like a 100% human.",
)
chat_session = model.start_chat(history=[])
# Eleven Labs API configuration
eleven_labs_api_key = "sk_9ac3d5449624c92f16ca187955853621355a5f0ac52572e3"
eleven_labs_url = "https://api.elevenlabs.io/v1/text-to-speech/aEO01A4wXwd1O8GPgGlF"
def chat_and_tts(user_input):
# Send the user's input to the chat session
response = chat_session.send_message(user_input)
response_text = response.text
# Eleven Labs text-to-speech request payload
payload = {
"text": response_text,
"voice_settings": {
"stability": 0,
"similarity_boost": 0
}
}
headers = {
"xi-api-key": eleven_labs_api_key,
"Content-Type": "application/json"
}
# Make the request to Eleven Labs API
tts_response = requests.post(eleven_labs_url, json=payload, headers=headers)
# Check if the response is successful and save the audio content to a file
if tts_response.status_code == 200:
audio_path = '/content/response_audio.mp3'
with open(audio_path, 'wb') as file:
file.write(tts_response.content)
return response_text, audio_path
else:
return response_text, None
# Gradio interface
def chat_interface(user_input):
response_text, audio_path = chat_and_tts(user_input)
return response_text, audio_path
# Create the Gradio UI
iface = gr.Interface(
fn=chat_interface,
inputs="text",
outputs=["text", "audio"],
title="Chat with Ath",
description="Ask any question and get a friendly response from Ath. The response will also be converted to speech.",
theme="huggingface"
)
# Launch the Gradio app
iface.launch() |