Welcome to this showcase of using pre-made AI models and Next.js 13 to build powerful AI applications, with the combined strengths of Hugging Face and ElevenLabs in this case.
-
Hugging Face: A leading provider of Natural Language Processing (NLP) tools and pre-trained AI models.
-
ElevenLabs: Specializes in AI voice intelligence, offering lifelike text-to-speech synthesis and voice cloning technologies.
This project was inspired by the Sophomore AI track offered by Learn Web3.
Take a look at a deployed and functioning version: AI Stuff
This project shows you how to use pre-trained AI models for:
- Object Detection: Use Facebook's DEtection TRansformer (DETR) model to identify objects within images.
- Stable Diffusion Image Generation: Generate high-quality images from text prompts using a stable diffusion model from Runwayml.
- AI-Generated Audio: Transform text into lifelike speech with advanced text-to-speech synthesis, leveraging ElevenLabs' vocal emotion and intonation expertise.
Feel free to explore and contribute to this repository to make the most out of these AI tools.
Clone this repository
git clone https://github.com/soos3d/ai-stuff-huggingface-elevenlabs.git
Go into the ai-stuff
directory and install dependencies
cd ai-stuff && npm ci
Rename .env.example
to .env and add your API keys
HUGGINGFACE_API_KEY="YOUR_HUGGINGFACE_KEY"
II_API_KEY="YOUR_ELEVEN_LABS_KEY"
Go on ElevenLabs and create new voices
Run the app
npm run dev