https://github.com/latentspaceexplorer/athene
Athene is a voice-controlled AI assistant that combines speech recognition, LLMs, and text-to-speech.
https://github.com/latentspaceexplorer/athene
kokoro langchain llm voice-assistant
Last synced: 4 months ago
JSON representation
Athene is a voice-controlled AI assistant that combines speech recognition, LLMs, and text-to-speech.
- Host: GitHub
- URL: https://github.com/latentspaceexplorer/athene
- Owner: LatentSpaceExplorer
- Created: 2025-02-09T20:07:12.000Z (8 months ago)
- Default Branch: main
- Last Pushed: 2025-02-09T20:10:20.000Z (8 months ago)
- Last Synced: 2025-02-09T21:22:11.627Z (8 months ago)
- Topics: kokoro, langchain, llm, voice-assistant
- Language: Python
- Homepage:
- Size: 93.8 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Athene
Athene is a voice-controlled AI assistant that can manage your tasks, read to you your clipboard content, and engage in natural conversations using LLMs.
## Features
- Voice recognition and processing with dual input methods:
- Hold-to-record button in the application window
- Global hotkey (Alt+Y) that works system-wide
- Natural language task management with persistent storage
- Text-to-speech responses using [Kokoro](https://github.com/thewh1teagle/kokoro-onnx)
- Read text from clipboard
- General conversation
- Modular plugin system for easy extension
## Usage
To record a message, you can either:
- Hold the "Hold to Record" button in the application window
- Hold Alt+Y anywhere on your system (works even when Athene is not focused)
Release the button or key combination to process and receive a response.
## Prerequisites
- Python 3.12 or higher
- NVIDIA GPU with CUDA support (recommended)
- Groq API key for LLM access
## Installation
1. Clone the repository
2. Install dependencies using uv (recommended) or pip:
```bash
uv sync
```
3. Set up environment variables:
- Create a `.env` file
- Add your Groq API key: `GROQ_API_KEY=your_key_here`
4. Download Kokoro models:
- Create a `models/kokoro` directory
- Add required model files:
- `kokoro-v1.0.onnx`
- `voices-v1.0.bin`
5. Run the application:
```bash
uv run ./athene.py
```
## Supported Commands
- Task Management: Add, remove, and list tasks
- Clipboard: Read your clipboard text
- General Conversation: Natural dialogue on various topics
## Planned Features
- [ ] Add support alternative LLMs backends (e.g. OpenAI, local)
- [ ] Voice activation by name (e.g. "Athene")
- [ ] Recurring tasks
- [ ] Additional plugins:
- [ ] Reminders
- [ ] Day planning
- [ ] Habit tracking
- [ ] Internet search
- [ ] File reading
## Technical Stack
- **Speech Recognition**: SpeechRecognition
- **NLP**: LangChain (currently only Groq is supported)
- **TTS**: Kokoro ONNX