CoolFace
Apppublic

Sniffernews/FTTS-Free-text-to-speech

sourceHugging Faceupdated 6mo agoView on Hugging Face
0likes
App README

Microsoft Neural TTS Studio v2.0 - Premium Edition

🎙️ Advanced Text-to-Speech with Natural Voices & Modern UI

✨ Features

🌍 Multi-Language Support

  • —English UI with full translation support
  • —Dutch UI (Nederlands)
  • —Spanish UI (Español)
  • —French UI (Français)
  • —Easy language switching

🎨 Beautiful Modern UI

  • —Premium gradient design with smooth animations
  • —Responsive layout for desktop, tablet, and mobile
  • —Dark/Light mode toggle
  • —Voice quality indicators (Premium/Natural)
  • —Interactive voice selection grid
  • —Real-time character counter with warnings

🗣️ 100+ Natural Neural Voices

  • —Premium Quality Voices with enhanced clarity
  • —Multiple Languages: English, Dutch, French, German, Spanish, Italian, Portuguese, Chinese, Japanese, Korean, Arabic, Russian, Hindi
  • —Gender Options: Male, Female voices
  • —Accent Variations: US, UK, Australian, Canadian, Indian, and more
  • —Voice Information Panel with detailed metadata

📱 Advanced Features

  • —50,000 Character Support (increased from 40,000)
  • —Device Download & Save functionality
  • —Text Highlighting Sync during playback
  • —Auto-download option
  • —Recent Voices quick selection
  • —Keyboard Shortcuts (Ctrl+Enter to speak, Ctrl+S to download)
  • —Audio Player with controls
  • —Enhanced Error Handling

🤖 AI Agent Ready

  • —Hugging Face CLI Compatible
  • —RESTful API endpoints
  • —FormData Support for better compatibility
  • —No JSON Parse Errors

🚀 Quick Start

Installation

bash
pip install flask edge-tts

Run Locally

bash
python3 app.py

Open: http://localhost:7860

Hugging Face Deployment

bash
# Install Hugging Face CLI
curl -LsSf https://hf.co/cli/install.sh | bash

# Add AI Agent Skills
hf skills add --claude --global

📋 API Endpoints

Generate Speech

http
POST /api/tts
Content-Type: multipart/form-data

t: Your text here (max 50,000 chars)
s: voice-code (e.g., en-US-JennyNeural)
r: speed (-50 to +50)
p: pitch (-50 to +50)

Download Audio

http
POST /api/download
Content-Type: multipart/form-data

t: Your text here
s: voice-code
r: speed
p: pitch
filename: custom-name.mp3

Get Available Voices

http
GET /api/voices

Version Info

http
GET /api/version

🎯 Voice Examples

Premium English Voices

  • —Jenny (en-US-JennyNeural) - Natural US Female
  • —Aria (en-US-AriaNeural) - Premium US Female
  • —Nova (en-US-NovaNeural) - Premium US Female
  • —Jenny Multi (en-US-JennyMultilingualV2Neural) - Multilingual

Natural Dutch Voices

  • —Fenna (nl-NL-FennaNeural) - Standard Dutch Female
  • —Maarten (nl-NL-MaartenNeural) - Standard Dutch Male
  • —Dena (nl-BE-DenaNeural) - Belgian Female

International Voices

  • —Sonia (en-GB-SoniaNeural) - British Female
  • —Katja (de-DE-KatjaNeural) - German Female
  • —Elvira (es-ES-ElviraNeural) - Spanish Female
  • —Elsa (it-IT-ElsaNeural) - Italian Female

🎛️ UI Features

Text Input

  • —Large textarea with character counter
  • —Real-time validation with color-coded warnings
  • —Multi-language placeholder text

Voice Selection

  • —Interactive grid with voice details
  • —Quality indicators (Premium/Natural)
  • —Filter by language preference
  • —Recent voices quick access

Audio Controls

  • —Speed Control: -50% to +50%
  • —Pitch Control: -50Hz to +50Hz
  • —Real-time preview of settings
  • —Visual feedback for all controls

Settings Panel

  • —Text Highlighting Toggle
  • —Auto-download Option
  • —Dark Mode Switch
  • —Voice Information Display
  • —Recent Voices History

🔧 Technical Features

Backend

  • —Flask web framework
  • —edge-tts for Microsoft Neural TTS
  • —FormData handling for better compatibility
  • —MD5 caching for performance
  • —Error handling with detailed messages

Frontend

  • —Modern CSS3 with animations
  • —Responsive design with CSS Grid
  • —Font Awesome icons
  • —JavaScript ES6+ features
  • —No external dependencies except icons

Performance

  • —Audio caching with MD5 hashing
  • —Lazy loading of voice list
  • —Optimized bundle size
  • —Fast API responses

🌐 Browser Compatibility

  • —✅ Chrome 90+
  • —✅ Firefox 88+
  • —✅ Safari 14+
  • —✅ Edge 90+
  • —✅ Mobile browsers

📱 Mobile Features

  • —Touch-friendly interface
  • —Responsive design for all screen sizes
  • —Mobile audio player controls
  • —Optimized performance for mobile devices

🔒 Privacy & Security

  • —No data storage on servers
  • —Client-side processing for UI
  • —Secure API endpoints
  • —No tracking or analytics

🎨 Customization

Colors & Themes

  • —CSS Variables for easy theming
  • —Dark/Light mode support
  • —Gradient backgrounds
  • —Consistent design system

Voice Settings

  • —Custom speed/pitch ranges
  • —Voice filtering by language
  • —Quality preferences
  • —Recent voice memory

📊 Version History

v2.0.0 - Premium Edition

  • —✨ Multi-language UI support
  • —✨ 100+ Natural Voices with quality indicators
  • —✨ Device Download functionality
  • —✨ Beautiful Modern UI with gradients
  • —✨ Text Highlighting sync
  • —✨ 50,000 Character support
  • —✨ Enhanced Error Handling
  • —✨ Dark Mode toggle
  • —✨ Recent Voices feature

v1.0.0 - Original Release

  • —✅ Basic TTS functionality
  • —✅ 60+ Voices support
  • —✅ 40,000 Character limit
  • —✅ Hugging Face CLI ready

🤝 Contributing

This is a Microsoft Neural TTS Studio project with advanced features for modern text-to-speech applications.

📄 License

This project uses Microsoft Edge TTS and follows their terms of service.

🆘 Support

For issues and feature requests, please check:

  1. 1.Voice compatibility with your region
  2. 2.Internet connection for TTS generation
  3. 3.Browser compatibility for UI features
  4. 4.Character limits for text input

Microsoft Neural TTS Studio v2.0 - Premium Text-to-Speech Experience 🎙️