A comprehensive AI platform that brings together multiple AI services for content creation, including voiceovers, image generation, video creation, music composition, code generation, and speech processing. This platform now includes an advanced AI feature that runs locally without the need for an external API.
The platform now includes admin and user portals to manage users and services.
The jules.google feature is now available.
- Premium Voice Generation: High-quality text-to-speech with multiple voice options
- Multiple Providers: Premium, Standard, and Fast voice generation
- Customizable Settings: Adjustable speech speed and voice selection
- Export Ready: Download generated audio in MP3 format
- AI Image Creation: Generate stunning images from text descriptions
- Stock Photo Search: Search and access Pexels stock photos
- Multiple Styles: Photorealistic, artistic, cartoon, abstract, and digital art
- Custom Dimensions: Various size options from 512x512 to 1024x768
- High Quality Output: Professional-grade image generation
- AI Video Creation: Generate videos from text prompts using cutting-edge AI
- Multiple Qualities: Standard (480p), HD (720p), and Full HD (1080p)
- Various Styles: Realistic, cinematic, animated, and artistic
- Flexible Duration: 3 to 15-second video clips
- Download Support: Export videos in MP4 format
- AI Music Composition: Create original music tracks from text descriptions
- Multiple Genres: Ambient, classical, electronic, rock, jazz, pop, and cinematic
- Flexible Duration: 15 seconds to 2 minutes
- Quality Options: Large, medium, and fast models for different needs
- Professional Output: High-quality audio generation
- Multi-Language Support: JavaScript, TypeScript, Python, PHP, Java, C#, Go, Rust
- Framework Integration: React, Vue, Angular, Django, Laravel, and more
- Smart Code Generation: Context-aware code creation with best practices
- Export Functionality: Download generated code with proper file extensions
- Speech-to-Text: Convert audio files to text with high accuracy
- Text-to-Speech: Generate natural-sounding speech from text
- Multiple Formats: Support for MP3, WAV, M4A audio files
- Real-time Processing: Fast and efficient audio processing
- Frontend: Next.js 13, React 18, TypeScript
- Styling: Tailwind CSS, shadcn/ui components
- Icons: Lucide React
- API Integration: RESTful APIs for multiple AI services
- State Management: React hooks (useState, useEffect)
- Build Tool: Next.js with static export support
-
Clone the repository
git clone <repository-url> cd fus-ai-model
-
Install dependencies
npm install
-
Set up environment variables
cp .env.example .env.local
-
Configure API keys (see Configuration section below)
-
Run the development server
npm run dev
-
Open your browser Navigate to
http://localhost:3000
The platform supports multiple AI service providers. Configure your API keys in the .env.local file:
# AI Service API Keys
NEXT_PUBLIC_GEMINI_API_KEY=your_gemini_api_key_here
NEXT_PUBLIC_ELEVEN_LABS_API_KEY=your_eleven_labs_api_key_here
NEXT_PUBLIC_FAI_API_KEY=your_fai_api_key_here
NEXT_PUBLIC_STABILITY_AI_API_KEY=your_stability_ai_api_key_here
NEXT_PUBLIC_REPLICATE_API_KEY=your_replicate_api_key_here
NEXT_PUBLIC_VEO_3_API_KEY=your_veo_3_api_key_here
NEXT_PUBLIC_PEXELS_API_KEY=your_pexels_api_key_here
NEXT_PUBLIC_DEEPSEEK_API_KEY=your_deepseek_api_key_here
NEXT_PUBLIC_LAMIA_API_KEY=your_lamia_api_key_here| Service | Purpose | Models Available |
|---|---|---|
| Google Gemini | Text & Code Generation | gemini-1.5-pro, gemini-1.5-flash, gemini-1.0-pro |
| Eleven Labs | Text-to-Speech | eleven_multilingual_v2, eleven_turbo_v2, eleven_monolingual_v1 |
| FAI | Fast Voice Generation | fai-premium, fai-standard, fai-fast |
| Stability AI | Image Generation | stable-diffusion-xl, stable-diffusion-3, stable-cascade |
| Google Veo 3 | Video Generation | veo-3-standard, veo-3-premium |
| Pexels | Stock Photos | pexels-api-v1 |
| DeepSeek AI | Code Generation | deepseek-coder-v2, deepseek-chat-v2 |
| Lamia AI | Creative Text | lamia-creative, lamia-standard |
| Replicate | Music Generation | musicgen-large, musicgen-medium, riffusion |
- Navigate to the homepage to see all available AI services
- Click on any service to access its dedicated page
- Configure your settings in the Settings page
- Enter your prompts and generate content
- Download or export your generated content
- Enter your text in the text area
- Select your preferred AI provider and voice
- Choose speech speed (slow, normal, fast)
- Click "Generate Voiceover"
- Play the audio and download when satisfied
- Describe the image you want to create
- Choose between AI generation or stock photo search
- Select style and dimensions (for AI generation)
- Click "Generate Image" or "Search Images"
- Download the result
- Provide a detailed video description
- Select duration, quality, and style
- Click "Generate Video"
- Preview and download the generated video
- Describe the music style and mood
- Choose genre, duration, and AI model
- Click "Generate Music"
- Listen to the preview and download
- Describe the code functionality you need
- Select programming language and framework
- Choose your preferred AI provider
- Click "Generate Code"
- Copy or download the generated code
- Speech-to-Text: Upload an audio file and convert to text
- Text-to-Speech: Enter text and generate speech audio
- Download transcriptions or audio files
- Modern UI/UX: Clean, professional interface with gradient backgrounds
- Responsive Design: Optimized for desktop, tablet, and mobile devices
- Dark Mode Support: Automatic theme detection and manual toggle
- Progress Indicators: Real-time generation progress tracking
- Export Functionality: Download all generated content
- Settings Management: Centralized API key and model configuration
fus-ai-model/
├── app/
│ ├── api/
│ │ └── ai/
│ │ ├── code/
│ │ ├── image/
│ │ ├── music/
│ │ ├── speech-to-text/
│ │ ├── video/
│ │ └── voiceover/
│ ├── code/
│ ├── image/
│ ├── music/
│ ├── settings/
│ ├── speech/
│ ├── video/
│ ├── voiceover/
│ ├── globals.css
│ ├── layout.tsx
│ └── page.tsx
├── components/
│ ├── ai-services/
│ └── ui/
├── lib/
├── public/
├── .env.example
├── next.config.js
├── package.json
├── tailwind.config.ts
└── tsconfig.json
npm run buildThe project is configured for static export:
npm run buildThe built files will be in the out/ directory, ready for deployment to any static hosting service.
- Vercel: Automatic deployment with Git integration
- Netlify: Drag and drop or Git-based deployment
- GitHub Pages: Static site hosting
- AWS S3: Static website hosting
- Any CDN: Upload the
out/folder contents
- API Key Protection: All API keys are stored securely in environment variables
- Client-Side Storage: Settings are stored locally in the browser
- No Server-Side Storage: No user data is stored on servers
- HTTPS Required: All API communications use HTTPS
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
Fus AI Model was developed by Jamachi Mauricennadi, CEO of FusionHubAI.com.ng
Jamachi Mauricennadi is a visionary technology leader and the CEO of FusionHubAI, a cutting-edge AI solutions company based in Nigeria. With extensive experience in artificial intelligence, machine learning, and software development, Jamachi has dedicated his career to making advanced AI technologies accessible to businesses and individuals across Africa and beyond.
Contact Information:
- Company: FusionHubAI
- Website: fushionhubai.com.ng
- Role: Chief Executive Officer
FusionHubAI is at the forefront of AI innovation in Nigeria, providing comprehensive AI solutions that empower businesses to leverage the power of artificial intelligence. The company specializes in:
- Custom AI model development
- AI integration services
- Machine learning consulting
- AI-powered application development
- Enterprise AI solutions
For support, feature requests, or bug reports:
- GitHub Issues: Create an issue in this repository
- Documentation: Check this README and inline code comments
- Community: Join our discussions in the Issues section
Stay updated with the latest features and improvements:
- Version: 1.0.0
- Last Updated: 2025
- Next.js Version: 13.5.1
- React Version: 18.2.0
- Next.js Team: For the amazing React framework
- Vercel: For hosting and deployment solutions
- shadcn/ui: For beautiful UI components
- Tailwind CSS: For utility-first CSS framework
- Lucide: For beautiful icons
- AI Service Providers: Google, Eleven Labs, Stability AI, and others
Built with ❤️ by Jamachi Mauricennadi | FusionHubAI
Empowering creativity through artificial intelligence