How much time will I actually save with Fazm?

Most users report saving 45-90 minutes per day on repetitive tasks. The biggest time savings come from email management (drafting replies, sorting, archiving), form filling (expense reports, CRM updates, applications), research (comparing products, gathering data from multiple sites), and social media (cross-posting, scheduling, replying). For example, booking a flight that normally takes 10 minutes of clicking through airline sites takes a single voice command with Fazm. Filing an expense report that requires opening a PDF, extracting numbers, and entering them into a spreadsheet becomes one spoken sentence. The more repetitive and multi-step your daily work is, the more time you get back.

What exactly can Fazm control?

Fazm controls everything you can do manually on your Mac. That includes mouse movements and clicks, keyboard typing, browser navigation and form filling, app switching, file management in Finder, and system-level actions. It uses direct browser DOM control for web interactions - meaning it reads and manipulates the actual page structure rather than taking screenshots and guessing where to click. For native macOS apps, Fazm uses accessibility APIs to interact with buttons, menus, text fields, and other UI elements. This works across any application: Chrome, Safari, VS Code, Slack, Figma, Terminal, Mail, Calendar, and more.

How is Fazm different from ChatGPT or Claude?

Chatbots like ChatGPT and Claude give you answers in a conversation window. Fazm takes action directly on your computer. When you say 'reply to Sarah's email,' Fazm opens your email app, finds Sarah's message, writes a contextual reply, and sends it. A chatbot would tell you what to write, but you still have to do all the clicking and typing yourself. Fazm moves your mouse, types on your keyboard, clicks buttons, and navigates between apps. It is a computer agent, not a chat assistant.

How does the memory layer work?

Fazm builds a personal knowledge graph by extracting information from your files, browsing history, conversations, and daily activity. Over time, it learns your contacts (names, emails, relationships), accounts and credentials, preferences (formatting, tone, scheduling habits), and frequently used workflows. In your first week, you might say 'Reply to Sarah's email, she's my cofounder, her email is sarah@acme.com.' By week four, you just say 'Reply to Sarah' because Fazm already knows who she is. By week eight, Fazm can draft the reply before you even ask. All of this data stays locally on your Mac - your knowledge graph never leaves your machine or gets sent to any cloud service.

Is Fazm safe? Can it mess up my computer?

Safety is built into every layer of Fazm. You watch every action in real-time on your screen - Fazm moves your mouse and types visibly, so there is nothing hidden. You can stop any action at any point by pressing a keyboard shortcut. Fazm also shows you what it plans to do before executing destructive actions like deleting files or sending emails, giving you a chance to confirm or cancel. Because Fazm is open source, the code is fully auditable on GitHub. There is no hidden behavior, no background processes making changes you cannot see, and no actions that bypass your screen.

What platforms does Fazm support?

Fazm currently supports macOS, running natively on both Apple Silicon (M1, M2, M3, M4) and Intel Macs. It is built with Swift and uses macOS-specific frameworks like ScreenCaptureKit for screen analysis and Accessibility APIs for app control, which is why macOS is the primary platform. Windows and Linux support are on the roadmap but do not have release dates yet. You can also control your Mac remotely from your phone using Fazm Remote, which gives you voice access to your desktop while you are away from your computer.

How does Fazm voice input work?

One keyboard shortcut activates push-to-talk. Hold the key, speak naturally about what you need done, and release. Fazm transcribes your speech locally using on-device models, so there is no network latency for the voice recognition step. You do not need wake words like 'Hey Siri' or 'OK Google' - just press and talk. You can also type commands into the floating toolbar if you prefer text input. Fazm understands natural language, so you do not need to memorize specific commands. Say 'book me a flight to Tokyo next Thursday' or 'find the cheapest AirPods on Amazon' and Fazm figures out the steps.

Is my data sent to the cloud?

Fazm processes screen analysis and memory entirely on your machine. The personal knowledge graph, file indexing, and screen capture all run locally. The only data that leaves your Mac is the intent - a text description of what you want to accomplish, which is sent to the AI model (Claude or GPT) for action planning. Your actual screen content, file contents, browsing history, and personal knowledge graph never leave your computer. Fazm is also open source, so you can verify exactly what data is transmitted by reading the code on GitHub. For users who need complete air-gapped operation, local model support is planned.

Building a Live Streaming Voice Flow with Push-to-Talk on macOS

Fazm Team·March 17, 2026·3 min read

voice push-to-talk macos live-streaming floating-ui

Building a Live Streaming Voice Flow with Push-to-Talk on macOS

The best AI interface is one that stays invisible until you need it. A floating control bar on macOS with push-to-talk AI chat achieves exactly that - hold a key, speak your command, release, and the agent executes. No window switching. No typing. No breaking your flow.

Why Push-to-Talk Beats Always-Listening

Always-listening voice assistants have a fundamental problem - they activate when you do not want them to and miss activation when you do. Push-to-talk eliminates both issues. You control exactly when the agent is listening, which means zero false activations and zero missed commands.

For live streaming and creative work, this is critical. You do not want your AI agent responding to something you said to your audience. You want it responding only when you deliberately hold the hotkey and address it directly.

The Floating Control Bar

A minimal floating toolbar sits at the edge of your screen. It shows the current state - idle, listening, processing, executing. When you hold the push-to-talk key, the bar expands slightly to show a waveform visualization. Release the key and it shrinks back to minimal.

The bar persists across all spaces and desktops using NSPanel with the appropriate window level. It never steals focus from your current application. It never appears in the app switcher. It is always there when you need it and invisible when you do not.

Streaming Voice Processing

The voice data streams to a local Whisper model as you speak, providing near-real-time transcription. By the time you release the push-to-talk key, the transcription is already complete. The agent processes the command immediately - no waiting for upload, transcription, and response.

Local processing also means your voice data never leaves your machine. For live streamers who discuss sensitive topics or handle private information, this privacy guarantee matters.

Connecting to Agent Actions

The transcribed command feeds directly into the desktop agent's action pipeline. "Open the project in Xcode" triggers accessibility API interactions. "Send that screenshot to the design channel" chains together screenshot capture, Slack navigation, and file upload. The voice interface is just the input method - the agent handles the rest.

Building a Live Streaming Voice Flow with Push-to-Talk on macOS

Building a Live Streaming Voice Flow with Push-to-Talk on macOS

Why Push-to-Talk Beats Always-Listening

The Floating Control Bar

Streaming Voice Processing

Connecting to Agent Actions

More on This Topic

Related Posts

Accessibility Tree Dumps Overflow LLM Context Windows - How to Fix It

Using Agent Teams as a Product Backend: Bridging Swift Desktop Apps to Claude Agent SDK

Most AI Agent Development Is Cloud-First - Here's Why Local-First Is Better