diff --git a/.gitignore b/.gitignore index 5b59762..50da8f0 100644 --- a/.gitignore +++ b/.gitignore @@ -6,4 +6,6 @@ \myenv /tailwind/* -*.log \ No newline at end of file +*.log +/temp_audio/* +app/temp_audio/* \ No newline at end of file diff --git a/app/ai.py b/app/ai.py index 142c87d..0b59da1 100644 --- a/app/ai.py +++ b/app/ai.py @@ -6,18 +6,25 @@ from openai import OpenAI import google.generativeai as genai from anthropic import Anthropic +from gtts import gTTS +import uuid +from bs4 import BeautifulSoup +import markdown load_dotenv() # Set up logging -logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s") +logging.basicConfig( + level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s" +) logger = logging.getLogger(__name__) + def chat_with_chatbot(messages: List[Dict[str, str]], apiKey: str, engine: str) -> str: if not apiKey: logger.error("API key is missing.") raise ValueError("API key is required for making API requests.") - + try: if engine == "groq": content = chat_with_groq(messages, apiKey) @@ -36,6 +43,7 @@ def chat_with_chatbot(messages: List[Dict[str, str]], apiKey: str, engine: str) logger.error(f"Error in chat_with_chatbot function with engine {engine}: {e}") raise + def chat_with_groq(messages: List[Dict[str, str]], apiKey: str) -> str: try: client = Groq(api_key=apiKey) @@ -48,6 +56,7 @@ def chat_with_groq(messages: List[Dict[str, str]], apiKey: str) -> str: logger.error(f"Error in chat_with_groq: {e}") raise + def chat_with_openai(messages: List[Dict[str, str]], apiKey: str) -> str: try: client = OpenAI(api_key=apiKey) @@ -60,6 +69,7 @@ def chat_with_openai(messages: List[Dict[str, str]], apiKey: str) -> str: logger.error(f"Error in chat_with_openai: {e}") raise + def chat_with_anthropic(messages: List[Dict[str, str]], apiKey: str) -> str: try: client = Anthropic(api_key=apiKey) @@ -73,6 +83,7 @@ def chat_with_anthropic(messages: List[Dict[str, str]], apiKey: str) -> str: logger.error(f"Error in chat_with_anthropic: {e}") raise + def chat_with_gemini(messages: List[Dict[str, str]], apiKey: str) -> str: try: genai.configure(api_key=apiKey) @@ -89,3 +100,29 @@ def chat_with_gemini(messages: List[Dict[str, str]], apiKey: str) -> str: except Exception as e: logger.error(f"Error in chat_with_gemini: {e}") raise + + +def markdown_to_text(markdown_text: str) -> str: + # Convert Markdown to HTML + html = markdown.markdown(markdown_text) + # Use BeautifulSoup to extract text + soup = BeautifulSoup(html, "html.parser") + return soup.get_text() + + +def text_to_mp3(text: str): + base_path = os.path.dirname( + os.path.abspath(__file__) + ) # Get the absolute path of the script + temp_audio_dir = os.path.join(base_path, "temp_audio") + os.makedirs(temp_audio_dir, exist_ok=True) + plain_text = markdown_to_text(text) + filename = f"{uuid.uuid4()}.mp3" + filepath = os.path.join(temp_audio_dir, filename) + # print(filepath) + + # Generate speech audio file + tts = gTTS(text=plain_text, lang="en") + tts.save(filepath) + + return filepath diff --git a/app/api_routes.py b/app/api_routes.py index 1b03aa5..c12b28a 100644 --- a/app/api_routes.py +++ b/app/api_routes.py @@ -1,19 +1,12 @@ -from flask import ( - Flask, - Blueprint, - request, - jsonify, - session, - Response, -) +from flask import Flask, Blueprint, request, jsonify, session, Response, send_file import re - +import os from sqlalchemy import func from .models import User, Chatbot, Chat, Image, Comment from sqlalchemy.exc import IntegrityError from flask_login import login_user from typing import Union, List, Optional, Dict -from .ai import chat_with_chatbot +from .ai import chat_with_chatbot, text_to_mp3 from .constants import BOT_AVATAR_API, USER_AVATAR_API from .helpers import create_default_chatbots from .data_fetcher import fetch_contribution_data @@ -690,3 +683,27 @@ def api_comment_chatbot(): except Exception as e: return jsonify({"success": False, "message": str(e)}), 500 + + +@api_bp.route("/api/tts", methods=["POST"]) +# @jwt_required() +def api_tts(): + try: + data = request.get_json() + text = data.get("text") + if not text: + return jsonify({"success": False, "message": "Text not found"}), 400 + + filepath = text_to_mp3(text) + print(filepath) + + response = send_file(filepath, as_attachment=True) + + @response.call_on_close + def remove_file(): + os.remove(filepath) + + return response + + except Exception as e: + return jsonify({"success": False, "message": str(e)}), 500 diff --git a/client/bun.lockb b/client/bun.lockb index 2c4007b..5302984 100755 Binary files a/client/bun.lockb and b/client/bun.lockb differ diff --git a/client/src/App.tsx b/client/src/App.tsx index d10108c..ee78b08 100644 --- a/client/src/App.tsx +++ b/client/src/App.tsx @@ -21,6 +21,7 @@ import ScrollToTop from "react-scroll-to-top"; import { ArrowBigUpDash } from "lucide-react"; import LeaderboardPage from "./pages/Leaderboard"; import ChatbotViewPage from "./pages/ChatbotView"; +import TextToSpeechDownload from "./pages/Test"; const queryClient = new QueryClient(); function App() { @@ -39,6 +40,7 @@ function App() { } /> } /> + } /> } /> } /> } /> diff --git a/client/src/components/modals/Tts-magic-modal.tsx b/client/src/components/modals/Tts-magic-modal.tsx new file mode 100644 index 0000000..af20bec --- /dev/null +++ b/client/src/components/modals/Tts-magic-modal.tsx @@ -0,0 +1,138 @@ +import { + AlertDialog, + AlertDialogContent, + AlertDialogDescription, + AlertDialogFooter, + AlertDialogHeader, + AlertDialogTitle, +} from "@/components/ui/alert-dialog"; +import { SERVER_URL } from "@/lib/utils"; +import { useTtsMagicModal } from "@/stores/modal-store"; +import axios from "axios"; +import { useEffect, useState } from "react"; +import { Button } from "../ui/button"; +import toast from "react-hot-toast"; +import { Textarea } from "../ui/textarea"; + +import { AudioLines, Download, X } from "lucide-react"; + +const markdownToPlainText = (markdown: string) => { + return markdown + .replace(/(\*\*|__)(.*?)\1/g, "$2") // Bold + .replace(/(\*|_)(.*?)\1/g, "$2") // Italics + .replace(/~~(.*?)~~/g, "$1") // Strikethrough + .replace(/`{1,2}(.*?)`{1,2}/g, "$1") // Inline code + .replace(/### (.*?)\n/g, "$1\n") // H3 + .replace(/## (.*?)\n/g, "$1\n") // H2 + .replace(/# (.*?)\n/g, "$1\n") // H1 + .replace(/>\s?(.*?)(?=\n|$)/g, "$1") // Blockquote + .replace(/^\s*\n/g, "") // Remove empty lines + .replace(/\n+/g, "\n") // Consolidate newlines + .trim(); // Trim whitespace +}; + +export default function TtsMagicModal() { + const modal = useTtsMagicModal(); + const { text: initialText } = modal.extras; + + const [text, setText] = useState(""); + const [loading, setLoading] = useState(false); + + // Set initial text when the modal opens + useEffect(() => { + if (modal.isOpen) { + setText(initialText); // Set the initial text from modal extras + } + }, [modal.isOpen, initialText]); // Depend on modal open state and initial text + + const downloadAudio = async () => { + setLoading(true); + try { + const response = await axios.post( + `${SERVER_URL}/api/tts`, + { text: markdownToPlainText(text) }, + { responseType: "blob" } + ); + const url = window.URL.createObjectURL(new Blob([response.data])); + const link = document.createElement("a"); + link.href = url; + link.setAttribute("download", "speech.mp3"); + document.body.appendChild(link); + link.click(); + link.remove(); + modal.onClose(); + } catch (error) { + toast.error("Error generating audio"); + console.error("Error generating audio", error); + } finally { + setLoading(false); + } + }; + + const downloadTextFile = () => { + // Convert Markdown to plain text + const plainText = markdownToPlainText(text); // For simplicity, using the existing text directly + const blob = new Blob([plainText], { type: "text/plain" }); + const url = window.URL.createObjectURL(blob); + const link = document.createElement("a"); + link.href = url; + link.setAttribute("download", "text.txt"); + document.body.appendChild(link); + link.click(); + link.remove(); + }; + + return ( + modal.onClose()}> + + + +
+

Convert Text to speech and download

+ +
+ + + text is converted to audio file in mp3 format that will be + downloaded automatically. + +
+