Chatin 🌟 web
Presenting ( Yumeko ) 🤦🏻 – an anime character, That you can talk to using 🎙️ speech-to-text OR text-to-speech, Powered by OpenAI ChatGPT model gpt-3.5-turbo, to generate human-like text based on context, and elevenlabs API to generate high-quality spoken audio in any voice, style, and language.
- 🚀 Next.js for fullstack framework javaScript.
- 🤖 Integrate Chatbot API with OpenAI.
- 👄 Yumeko speaks using elevenlabs technology.
- 🖼️ Chat markdown support: Links and Images.
- 🎙️ Speech-to-Text Realtime voice cloning.
- 🌍 Speech transcript supports multiple languages.
- 💾 Automatically saves chat history to localStorage.
- 📸 Take a screenshot image of your chat.
- ⏱️ Real-time streamed Chatbot responses.
- 🔒 Secured, Rate-limited API routes to prevent abuse.
Here's a rundown of the technologies and tools 📝 I've used to build this App:
Name | Link |
---|---|
Framework | Next.js |
Database | Supabase |
Deployment | Vercel |
Favicon | Iconify |
Styling | TailwindCSS |
This app is hosted and deployed in Vercel for many futures to get the best user-end performance like > automatic scaling, easy integration with git, easy configuration, and more..
In this app, i use Speech Recognition and it's an npm package called react-speech-recognition that can activate the microphone and turn the user's speech into text that it can process to ChatGPT.
It supported multiple 🌍 languages like:
- English
- Arabic
- Japanese
- Korean
- Russian
- German
- French
- Turkish
It is recommended to open this app web with Google Chrome 🌐 since other browsers do not support speech recognition.
Note: Speech recognition is not supported on 📱 mobile devices.
If you have any questions or feedback, please reach out to me at discord or mail@omar11.sa
Contributions, issues and feature requests are welcome!
Give a ⭐️ if this project helped you!
Your support will help me improve this project, and pay my API bills, and it will help me also keep this App running at its best, Thank you anyway for visiting my GitHub repo 💖