This is a project files for a workshop to create your digital assistant with speech and video animation functions.
The structure of the repo is that every step have its own branch. You can start from any of them or go to the 'final' directly to get the final code.
- main Basic setup, required packages and app structure.
- basic_ui Setting up basic user interface and storage.
- conversationConversation model. Memory. Multiple conversations.
- speech Elevenlabs api for a text-to-speech. Managing audio files and different way to use api.
- video D-ID api for a text-to-video
- final Updating user interface for a chat-like assistant. Connecting everything together.
First, clone the project and install required packages
npm iStart development server
npm run dev
# or
yarn dev
# or
pnpm devOpen http://localhost:3000 with your browser to see the result.