README.md

---
title: Emoti Voice AI
emoji: 💬
colorFrom: yellow
colorTo: purple
sdk: gradio
sdk_version: 5.0.1
app_file: app.py
pinned: false
---
# 🎤 Advanced OpenAI Text-to-Speech Generator

Convert text to natural-sounding speech with emotion detection and multi-language support. This application uses advanced AI techniques to detect emotions in text and adjusts speech parameters accordingly.

## Features

- 🎭 **Emotion Detection**: Automatically detects emotions in text
- 😄 **Emoji Responses**: Visual emotion indicators
- 🌍 **Multi-language Support**: Auto-translation to English
- � **Dynamic Speed Adjustment**: Emotion-based speed tuning
- 🎚️ **Voice Selection**: Multiple voice styles
- 🔒 **Secure**: API keys are not stored

## How to Use

1. Get your [OpenAI API key](https://platform.openai.com/account/api-keys)
2. Enter text in any language
3. Adjust settings (voice, speed, emotion intensity)
4. Click "Generate Speech"
5. Play/download the generated audio

## Technical Details

- **Emotion Model**: `j-hartmann/emotion-english-distilroberta-base`
- **Translation**: Google Translate API
- **TTS Engine**: OpenAI's `tts-1` model
- **UI Framework**: Gradio

## Limitations

- Requires OpenAI API credits
- Max 4096 characters per request
- Translation accuracy varies by language

[![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces)

An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).