openvoice_realtime_conversation.mp4

✉️ Get notified when the packaged version releases

The Offline AI interface for Hackers, Makers, and Builders
🐞 Report Bug	✨ Request Feature	🛡️ Report Vulnerability	🛡️ Wiki

✨ Key Features
🗣️ Real-time conversations
- Three speech engines: espeak, SpeechT5, OpenVoice - Auto language detection (OpenVoice) - Real-time voice-chat with LLMs
🤖 Customizable AI Agents
- Custom agent names, moods, personalities - Retrieval-Augmented Generation (RAG) - Create AI personalities and moods
📚 Enhanced Knowledge Retrieval
- RAG for documents/websites - Use local data to enrich chat
🖼️ Image Generation & Manipulation
- Text-to-Image (Stable Diffusion 1.5, SDXL, Turbo) - Drawing tools & ControlNet - LoRA & Embeddings - Inpainting, outpainting, filters
🌍 Multi-lingual Capabilities
- Partial multi-lingual TTS/STT/interface - English & Japanese GUI
🔒 Privacy and Security
- Runs locally, no external API (default) - Customizable LLM guardrails & image safety - Disables HuggingFace telemetry - Restricts network access
⚡ Performance & Utility
- Fast generation (~2s on RTX 2080s) - Docker-based setup & GPU acceleration - Theming (Light/Dark/System) - NSFW toggles - Extension API - Python library & API support

🌍 Language Support

Language	TTS	LLM	STT	GUI
English	✅	✅	✅	✅
Japanese	✅	✅	❌	✅
Spanish	✅	✅	❌	❌
French	✅	✅	❌	❌
Chinese	✅	✅	❌	❌
Korean	✅	✅	❌	❌

🫰 Request language support

💾 Installation Quick Start

⚙️ System Requirements

Specification	Minimum	Recommended
OS	Ubuntu 22.04, Windows 10	Ubuntu 22.04 (Wayland)
CPU	Ryzen 2700K or Intel Core i7-8700K	Ryzen 5800X or Intel Core i7-11700K
Memory	16 GB RAM	32 GB RAM
GPU	NVIDIA RTX 3060 or better	NVIDIA RTX 4090 or better
Network	Broadband (used to download models)	Broadband (used to download models)
Storage	22 GB (with models), 6 GB (without models)	100 GB or higher

🔧 Installation Steps

1. Install system requirements

   sudo apt update && sudo apt upgrade -y
   sudo apt install -y make build-essential libssl-dev zlib1g-dev libbz2-dev libreadline-dev libsqlite3-dev wget curl llvm libncurses5-dev libncursesw5-dev xz-utils tk-dev libffi-dev liblzma-dev python3-openssl git nvidia-cuda-toolkit pipewire libportaudio2 libxcb-cursor0 gnupg gpg-agent pinentry-curses espeak xclip cmake qt6-qpa-plugins qt6-wayland qt6-gtk-platformtheme mecab libmecab-dev mecab-ipadic-utf8 libxslt-dev
   sudo apt install espeak
   sudo apt install espeak-ng-espeak

2. Create airunner directory

   sudo mkdir ~/.local/share/airunner
   sudo chown $USER:$USER ~/.local/share/airunner

3. Install AI Runner - Python 3.13+ required pyenv and venv are recommended (see wiki for more info)

   pip install "typing-extensions==4.13.2"
   pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
   pip install airunner[all_dev]
   pip install -U timm

4. Run AI Runner

   airunner

For more options, including Docker, see the Installation Wiki.

---

Basic Usage

• Run AI Runner: airunner
• Run the downloader: airunner-setup
• Build templates: airunner-build-ui

---

🤖 Models

These are the sizes of the optional models that power AI Runner. Modality Size Text-to-Speech OpenVoice (Voice) 4.0 GB Speech T5 (Voice) 654.4 MB Speech-to-Text Whisper Tiny 155.4 MB Text Generation Ministral 8b (default) 4.0 GB Whisper Tiny 155.4 MB Ollama (various models) 1.5 GB - 20 GB OpenRouter (various models) 1.5 GB - 20 GB Huggingface (various models) 1.5 GB - 20 GB Ministral instruct 8b (4bit) 5.8 GB Image Generation Controlnet (SD 1.5) 10.6 GB Controlnet (SDXL) 320.2 MB Safety Checker + Feature Extractor 3.2 GB SD 1.5 1.6 MB SDXL 1.0 6.45 MB Stack AI Runner uses the following stack SQLite: For local data storage Alembic: For database migrations SQLAlchemy: For ORM Pydantic: For data validation http.server: Basic local server for static files PySide6: For the GUI A variety of other libraries for TTS, STT, LLMs, and image generation

✨ LLM Vendors Default local model: Ministral 8b instruct 4bit Ollama:: A variety of local models to choose from (requires Ollama CLI) OpenRouter: Remove server-side LLMs (requires API key) Huggingface: Coming soon 🎨 Art Models By default, AI Runner installs essential TTS/STT and minimal LLM components, but AI art models must be supplied by the user. Organize them under your local AI Runner data directory: ~/.local/share/airunner ├── art │ └── models │ ├── SD 1.5 │ │ ├── controlnet │ │ ├── embeddings │ │ ├── inpaint │ │ ├── lora │ │ └── txt2img │ ├── Flux (not supported yet) │ ├── SDXL 1.0 │ │ ├── controlnet │ │ ├── embeddings │ │ ├── inpaint │ │ ├── lora │ │ └── txt2img │ └── SDXL Turbo │ ├── controlnet │ ├── embeddings │ ├── inpaint │ ├── lora │ └── txt2img Optional third-party services OpenStreetMap: Map API OpenMeteo: Weather API

---

Contributing

We welcome pull requests for new features, bug fixes, or documentation improvements. You can also build and share extensions to expand AI Runner’s functionality. For details, see the Extensions Wiki.

Take a look at the Contributing document and the Development wiki page for detailed instructions.

🧪 Testing & Test Organization

AI Runner uses pytest for all automated testing. Test coverage is a priority, especially for utility modules.

Test Directory Structure

• Headless-safe tests:
  • Located in src/airunner/utils/tests/
  • Can be run in any environment (including CI, headless servers, and developer machines)
  • Run with:

    pytest src/airunner/utils/tests/

• Display-required (Qt/Xvfb) tests:
  • Located in src/airunner/utils/tests/xvfb_required/
  • Require a real Qt display environment (cannot be run headlessly or with pytest-qt)
  • Typical for low-level Qt worker/signal/slot logic
  • Run with:

    xvfb-run -a pytest src/airunner/utils/tests/xvfb_required/
    # Or for a single file:
    xvfb-run -a pytest src/airunner/utils/tests/xvfb_required/test_background_worker.py

  • See the README in xvfb_required/ for details.

CI/CD

• By default, only headless-safe tests are run in CI.
• Display-required tests are intended for manual or special-case runs (e.g., when working on Qt threading or background worker code).
• (Optional) You may automate this split in CI by adding a separate job/step for xvfb tests.

General Testing Guidelines

• All new utility code must be accompanied by tests.
• Use pytest, pytest-qt (for GUI), and unittest.mock for mocking dependencies.
• For more details on writing and organizing tests, see the project coding guidelines and the src/airunner/utils/tests/ folder.

Development & Testing

• Follow the copilot-instructions.md for all development, testing, and contribution guidelines.
• Always use the airunner command in the terminal to run the application.
• Always run tests in the terminal (not in the workspace test runner).
• Use pytest and pytest-cov for running tests and checking coverage.
• UI changes must be made in .ui files and rebuilt with airunner-build-ui.

Documentation

• See the Wiki for architecture, usage, and advanced topics.

Module Documentation

• API Service Layer
• Main Window Model Load Balancer
• Facehugger Shield Suite
• NodeGraphQt Vendor Module
• Xvfb-Required Tests
• ORM Models

For additional details, see the Wiki.