Open Advanced
Voice Assistant

AI always by your side

Let's work together naturally. Talk to me like a friend, and I'll help you get things done - whether you're online or offline, I'm here to make your day easier.

How It Works

DecisionsAI is your personal voice assistant that runs directly on your operating system. It works completely offline by default, keeping your data private and secure. However, if you want to enhance its capabilities, you can easily connect it to powerful cloud services.

The assistant processes your voice commands through four key stages, each optimized for performance and flexibility. You can customize each stage to run locally or in the cloud based on your needs.

Speech-to-Text

Converts your voice commands into text with high accuracy, ensuring clear command recognition in any environment.

Language Model

Processes your commands intelligently, understanding context and determining the best way to assist you.

Text-to-Speech

Transforms responses into natural-sounding speech, creating a fluid and engaging conversation experience.

Playback Module

Delivers smooth, natural-sounding responses with seamless transitions between sentences.

By default, DecisionsAI runs completely offline using high-quality local processing. This ensures your privacy and allows you to use the assistant anywhere, anytime.

Want to enhance your experience? Simply add your API keys in the preferences to unlock cloud-based features. Connect to OpenAI or Claude for advanced language understanding, AssemblyAI for professional-grade speech recognition, or ElevenLabs for premium voice synthesis. Configure each stage in the app's preferences window.

Powerful Features

DecisionsAI transforms how you interact with your computer, making complex tasks simple through voice commands and AI intelligence.

Online & Offline

Work seamlessly whether you're connected to the internet or completely offline with local models.

Interoperable Models

Switch between OpenAI or local Ollama models like Llama 3.3 based on your needs and preferences.

Voice Commands

Control your entire system with natural language commands that feel intuitive and responsive.

App Management

Seamlessly open, close, and switch between applications without touching your keyboard or mouse.

Dictation & Input

Dictate text or code into any application with high accuracy and natural language understanding.

Custom Voices

Experience celebrity voice interactions with ElevenLabs' API, or select from Kokoro's high-quality default voice choices.

Processing Options

Choose from a variety of processing options for voice and language tasks, with the flexibility to run locally or in the cloud.

Voice Models

Speech Recognition

Default to Vosk for lightweight offline processing, or choose Whisper.cpp for local high-accuracy transcription, or AssemblyAI's SLAM-1 for cloud-based performance with real-time streaming and advanced audio intelligence. Features intelligent VAD threshold detection and echo cancellation.

ElevenLabs

Premium voice synthesis with access to ElevenLabs' latest models including v2 and v3. Features voice cloning, emotion control, and ultra-realistic speech patterns with your API key.

Kokoro TTS

High-performance local TTS with multiple voice options. Optimized for low-latency response and offline operation, with configurable speech parameters and voice styles.

Language Models

OpenAI Models

Access GPT-4 Turbo, GPT-4, and GPT-3.5 Turbo through your OpenAI API key. Perfect for complex reasoning, creative tasks, and general conversation with industry-leading performance.

Customizable Ollama Models

Default to Gemma 3:4b for general tasks, with support for any Ollama model. Specialize with separate models for conversation (e.g., Mistral) and logical reasoning (e.g., CodeLlama). Full control over model parameters and context windows.

LangChain Integration

Advanced RAG with local folder indexing, persistent chat history, and conversation review UI. Supports document chunking, embedding generation, and semantic search with configurable parameters.