# Altic Altic builds local-first AI productivity software for macOS and developer workflows. ## Products - FluidVoice: Free open source voice-to-text for macOS. Local-first dictation with Parakeet, Apple Speech, Whisper, AI enhancement, command mode, write mode, and Intel support through Whisper. URL: https://altic.dev/fluid Markdown: https://altic.dev/fluid.md Source-of-truth README: https://github.com/altic-dev/FluidVoice Latest release: https://github.com/altic-dev/Fluid-oss/releases/latest - Altic MCP: Open source macOS automation MCP server for Claude Desktop and other MCP clients with 37 exact tools, Chrome CDP browser control, Safari automation, screen capture, and altic-studio skill support. URL: https://altic.dev/mcp Markdown: https://altic.dev/mcp.md Tool inventory JSON: https://altic.dev/mcp/tools.json Repository: https://github.com/altic-dev/altic-mcp ## Site - Sitemap: https://altic.dev/sitemap.xml - Privacy: https://altic.dev/privacy-policy - Contact: https://altic.dev/contact --- # FluidVoice FluidVoice is a fully open source voice-to-text dictation app for macOS with local speech models, AI enhancement, global hotkeys, smart typing into any app, command mode, write mode, live preview, history, and stats. Canonical URL: https://altic.dev/fluid Markdown URL: https://altic.dev/fluid.md Source-of-truth README: https://github.com/altic-dev/FluidVoice Latest release: https://github.com/altic-dev/Fluid-oss/releases/latest Build/source repository from README: https://github.com/altic-dev/Fluid-oss ## Quick Facts - Platform: macOS 15.0 Sequoia or later - Hardware: Apple Silicon; Intel supported from 1.5.1 builds using Whisper - Price: Free - License: GPLv3 from 2026-02-23 onward - Primary models: Parakeet Flash, Parakeet TDT v3/v2, Cohere Transcribe, Apple Speech, Whisper - Privacy: Local-first; optional anonymous analytics; optional AI provider keys stored in macOS Keychain ## Requirements - macOS 15.0 (Sequoia) or later - Apple Silicon Mac (M1, M2, M3, M4) - Intel Macs supported from 1.5.1 builds using Whisper models - Microphone access - Accessibility permissions for typing ## Features - Live Preview Mode with real-time transcription preview in the overlay - Multiple speech models: Parakeet Flash, Parakeet TDT v3 and v2, Cohere Transcribe, Apple Speech, and Whisper - Real-time transcription with extremely low latency - AI enhancement with OpenAI, Groq, and custom providers - Global hotkey for instant voice capture - Smart typing directly into any app - Menu bar integration - Auto-updates with seamless restart - Opt-in beta channel - Command Mode for taking actions on the Mac by voice - Write Mode for writing or rewriting text in any text box - History stats and usage stats ## Supported Speech Models | Model |Best for |Language support |Download size |Hardware | | --- | --- | --- | --- | --- | | Parakeet Flash (Beta) | Lowest-latency live English dictation | English only | ~250 MB | Apple Silicon | | Parakeet TDT v3 | Fast default multilingual dictation | 25 languages | ~500 MB | Apple Silicon | | Parakeet TDT v2 | Fastest English-only dictation | English only | ~500 MB | Apple Silicon | | Cohere Transcribe | High-accuracy multilingual dictation | 14 languages | ~1.4 GB | Apple Silicon | | Apple Speech | Zero-download native macOS speech recognition | System languages available on the user's Mac | Built in | Apple Silicon and Intel | | Whisper Tiny / Base / Small / Medium / Large | Broad compatibility, including Intel Macs | Up to 99 languages depending on selected model size | ~75 MB to ~2.9 GB | Apple Silicon and Intel | ## Model Notes - Parakeet Flash is the best pick when words need to appear live with the lowest latency. - Parakeet TDT v3 remains the default multilingual Apple Silicon model. - Cohere Transcribe is the stronger pick for a larger multilingual model with higher displayed accuracy. - Whisper remains the fallback for Intel Macs and the widest language coverage. ## Language Details ### Parakeet Flash Languages English. ### Parakeet TDT v3 Languages Bulgarian, Croatian, Czech, Danish, Dutch, English, Estonian, Finnish, French, German, Greek, Hungarian, Italian, Latvian, Lithuanian, Maltese, Polish, Portuguese, Romanian, Russian, Slovak, Slovenian, Spanish, Swedish, and Ukrainian. ### Parakeet TDT v2 Languages English. ### Cohere Transcribe Languages English, French, German, Italian, Spanish, Portuguese, Greek, Dutch, Polish, Mandarin, Japanese, Korean, Vietnamese, and Arabic. ### Apple Speech Languages System language support depends on the macOS speech recognition languages available on the user's machine. ### Whisper Language Support Whisper supports up to 99 languages, depending on the selected model size. ## Quick Start 1. Download the latest release. 2. Move FluidVoice to the Applications folder. 3. Grant microphone and accessibility permissions when prompted. 4. Set a preferred hotkey in settings. 5. Optionally add an AI provider API key for enhanced transcription. Keys are stored securely in macOS Keychain. 6. Optionally opt in to beta builds in Settings -> Automatic Updates -> Beta Releases. ## Privacy and Analytics FluidVoice is local-first. Optional anonymous analytics exist for usage, reliability, and release health, but the README states that voice, raw audio, transcribed text, selected text, prompts, AI-generated responses, terminal commands, window titles, file paths, clipboard content, and typed content are not collected. ### Anonymous analytics may collect - App version, build, and macOS version - Low-cardinality feature/config flags, such as app mode and major settings - Approximate usage ranges - High-level success/error outcomes ### Anonymous analytics does not collect - Voice, raw audio, or transcribed text - Selected text, prompts, or AI-generated responses - Terminal commands or outputs - Window titles, file names, file paths, clipboard content, or typed content - Personal or private information Disable path: Settings -> Share Anonymous Analytics ## Demo Transcript Summaries - Command Mode: Command Mode lets a user speak an instruction and have FluidVoice take an action on the Mac. - Write Mode: Write Mode lets a user write or rewrite selected text in any text box in any Mac app. - Dictation Mode: Dictation Mode captures speech and types the resulting text into the active text field. ## FAQ ### Is FluidVoice free? Yes. The FluidVoice README describes the project as completely free and open source. ### What macOS version does FluidVoice require? FluidVoice requires macOS 15.0 Sequoia or later, plus microphone access and accessibility permissions for typing. ### Does FluidVoice support Intel Macs? Yes. The README states that Intel Macs are supported from 1.5.1 builds using Whisper models. ### Which speech models does FluidVoice support? FluidVoice supports Parakeet Flash (Beta), Parakeet TDT v3, Parakeet TDT v2, Cohere Transcribe, Apple Speech, and Whisper Tiny/Base/Small/Medium/Large. ### How many languages does FluidVoice support? Language support is model-specific: Parakeet Flash and Parakeet TDT v2 are English-only, Parakeet TDT v3 supports 25 languages, Cohere Transcribe supports 14 languages, Apple Speech depends on macOS system languages, and Whisper supports up to 99 languages depending on model size. ### Does FluidVoice work offline? FluidVoice is local-first and uses local speech models for dictation. AI enhancement can use optional providers such as OpenAI, Groq, or custom providers, so cloud use depends on the features and providers a user enables. ### What permissions does FluidVoice need? FluidVoice needs microphone access for voice capture and accessibility permissions for typing into other apps. ### What license does FluidVoice use? From 2026-02-23 onward, FluidVoice is licensed under the GNU General Public License v3.0 (GPLv3). Versions before that date used Apache License 2.0. ### What does FluidVoice analytics collect? Optional anonymous analytics can include app version, build, macOS version, low-cardinality feature/config flags, approximate usage ranges, and high-level success or error outcomes. The README says it does not collect voice, raw audio, transcribed text, selected text, prompts, AI-generated responses, terminal commands, window titles, file paths, clipboard content, typed content, or personal/private information. ### Where can I download FluidVoice? The FluidVoice README points users to the latest release at https://github.com/altic-dev/Fluid-oss/releases/latest. --- # Altic MCP Altic MCP turns Claude into a hands-on Mac operator. Connect 37 precise tools for Messages, Contacts, Notes, Reminders, Calendar, Safari, Chrome CDP, screen capture, system controls, and visual feedback, all through an open source Model Context Protocol server for macOS. Canonical URL: https://altic.dev/mcp Markdown URL: https://altic.dev/mcp.md Tool inventory JSON: https://altic.dev/mcp/tools.json Repository: https://github.com/altic-dev/altic-mcp Server source: https://github.com/altic-dev/altic-mcp/blob/main/server.py ## Quick Facts - Category: Model Context Protocol server and macOS automation tool - License: Apache-2.0 - README tool claim: 20+ tools - Exact server.py tool count: 37 - Skill: altic-studio - Requirements: macOS 10.13+; Python 3.13+; UV package manager; Google Chrome for Chrome CDP tools ## Requirements - macOS 10.13+ - Python 3.13+ - UV package manager - Google Chrome for Chrome CDP tools ## Setup 1. Install UV if needed ```bash curl -LsSf https://astral.sh/uv/install.sh | sh ``` 2. Clone and set up the repository ```bash git clone https://github.com/altic-dev/altic-mcp.git && cd altic-mcp && uv sync ``` 3. Test locally ```bash uv run server.py ``` 4. Configure Claude Desktop ```bash uv run --project /FULL/PATH/TO/altic-mcp /FULL/PATH/TO/altic-mcp/server.py ``` ## Skill Installation ```bash npx skills add altic-dev/altic-mcp --list ``` ```bash npx skills add altic-dev/altic-mcp ``` ## Required Permissions - Contacts for search_contacts - Calendars for calendar events - Reminders for creating reminders - Automation so Claude can control apps such as Messages, Notes, and Safari - Accessibility for screen glow and system controls - Screen Recording for screenshot capture tools - Safari -> Develop -> Allow JavaScript from Apple Events for Safari tools - Google Chrome for Chrome CDP tools ## Tool Categories ### Messages & Contacts (3 tools) Send and read iMessages, search contacts, and resolve phone numbers. - `search_contacts` - `send_imessage` - `read_recent_messages` ### Notes & Reminders (3 tools) Create and search Apple Notes, then create time-based reminders. - `create_note` - `search_notes` - `set_reminder` ### Calendar (2 tools) Create Calendar events and list events for a specific day. - `create_calendar_event` - `list_calendar_events_for_day` ### Safari (12 tools) Control Safari tabs, windows, navigation, history, JavaScript, and page inspection. - `open_safari_tab` - `close_safari_tab` - `get_safari_tabs` - `switch_safari_tab` - `run_safari_javascript` - `navigate_safari` - `reload_safari_page` - `safari_go_back` - `safari_go_forward` - `open_safari_window` - `close_safari_window` - `get_safari_page_info` ### Chrome CDP (9 tools) Use session-based Chrome DevTools Protocol control for navigate, wait, click, type, extract, screenshot, and close workflows. - `chrome_open_session` - `chrome_list_sessions` - `chrome_navigate` - `chrome_wait_for` - `chrome_click` - `chrome_type` - `chrome_extract` - `chrome_screenshot` - `chrome_close_session` ### Screen Capture (1 tools) Capture the active display and return image output directly to the model. - `capture_active_screen` ### System (5 tools) Open apps and adjust brightness or system volume. - `open_app` - `decrease_brightness` - `increase_brightness` - `turn_up_volume` - `turn_down_volume` ### Visual Feedback (2 tools) Add and remove a screen glow so the user can see when automation is active. - `add_screen_glow` - `remove_screen_glow` ## Exact Tool Inventory ### open_app Category: System Open any macOS application by name. Arguments: - `name` (string, required): Name of the Mac app, such as Mail, Contacts, or Messages. Permissions: Automation ### send_imessage Category: Messages & Contacts Send an iMessage to a phone number. Arguments: - `phone_number` (string, required): Recipient phone number. - `message` (string, required): Message text to send. Permissions: Contacts, Automation ### search_contacts Category: Messages & Contacts Search Contacts by name and return matching people and phone numbers. Arguments: - `name` (string, required): Contact name to search for. Permissions: Contacts ### read_recent_messages Category: Messages & Contacts Read recent iMessages between the user and a phone number. Arguments: - `phone_number` (string, required): Phone number for the conversation. - `recent_message_count` (integer, optional, default 25): Number of recent messages to retrieve, 1 to 200. Permissions: Automation ### set_reminder Category: Notes & Reminders Create a macOS reminder with a specific date, time, and list. Arguments: - `name` (string, required): Reminder text. - `datetime` (string, required): Time in YYYY-MM-DD HH:MM format. - `list_name` (string, optional, default Reminders): Reminder list name. Permissions: Reminders ### create_note Category: Notes & Reminders Create a note in Apple Notes. Arguments: - `name` (string, required): Note title. - `body` (string, required): Note body. - `folder` (string, optional): Optional folder. Uses default folder if omitted. Permissions: Automation ### search_notes Category: Notes & Reminders Search Apple Notes. Arguments: - `query` (string, required): Search query. - `max_results` (integer, optional, default 10): Maximum results, 1 to 20. Permissions: Automation ### decrease_brightness Category: System Decrease screen brightness. Arguments: - `amount` (number, optional, default 0.0625): Brightness decrement on a 0.0 to 1.0 scale. Permissions: Accessibility ### increase_brightness Category: System Increase screen brightness. Arguments: - `amount` (number, optional, default 0.0625): Brightness increment on a 0.0 to 1.0 scale. Permissions: Accessibility ### turn_up_volume Category: System Turn up system volume. Arguments: - `amount` (number, optional, default 6.25): Volume increase on a 0 to 100 scale. Permissions: Accessibility ### turn_down_volume Category: System Turn down system volume. Arguments: - `amount` (number, optional, default 6.25): Volume decrease on a 0 to 100 scale. Permissions: Accessibility ### create_calendar_event Category: Calendar Create an event in macOS Calendar. Arguments: - `title` (string, required): Event title. - `start_datetime` (string, required): Start date and time in YYYY-MM-DD HH:MM format. - `duration_minutes` (integer, required): Duration in minutes. - `calendar_name` (string, optional): Optional calendar name. Uses default calendar if omitted. Permissions: Calendars ### list_calendar_events_for_day Category: Calendar List Calendar events for a specific day. Arguments: - `date` (string, required): Date in YYYY-MM-DD format. Permissions: Calendars ### open_safari_tab Category: Safari Open a new Safari tab with an optional URL. Arguments: - `url` (string, optional): Optional URL to open. Permissions: Automation, Safari JavaScript from Apple Events ### close_safari_tab Category: Safari Close a Safari tab. Arguments: - `tab_index` (integer, optional, default -1): Use -1 for current tab or a 1-based tab index. Permissions: Automation ### get_safari_tabs Category: Safari List all open Safari tabs with URLs and titles. Arguments: No arguments. Permissions: Automation ### switch_safari_tab Category: Safari Switch to a Safari tab by 1-based index. Arguments: - `tab_index` (integer, required): 1-based tab index. Permissions: Automation ### run_safari_javascript Category: Safari Execute JavaScript in the current Safari tab. Arguments: - `javascript_code` (string, required): JavaScript code to execute. Permissions: Automation, Safari JavaScript from Apple Events ### navigate_safari Category: Safari Navigate the current Safari tab to a URL. Arguments: - `url` (string, required): Destination URL. Permissions: Automation ### reload_safari_page Category: Safari Reload the current Safari page. Arguments: No arguments. Permissions: Automation ### safari_go_back Category: Safari Navigate back in Safari history. Arguments: No arguments. Permissions: Automation ### safari_go_forward Category: Safari Navigate forward in Safari history. Arguments: No arguments. Permissions: Automation ### open_safari_window Category: Safari Open a new Safari window with an optional URL. Arguments: - `url` (string, optional): Optional URL to open. Permissions: Automation ### close_safari_window Category: Safari Close the current Safari window. Arguments: No arguments. Permissions: Automation ### get_safari_page_info Category: Safari Get current Safari page URL, title, text content, and HTML source. Arguments: No arguments. Permissions: Automation, Safari JavaScript from Apple Events ### chrome_open_session Category: Chrome CDP Open a Chrome automation session for browser control. Arguments: - `start_url` (string, optional, default about:blank): Initial page URL. - `debug_port` (integer, optional, default 9222): Chrome remote debugging port, 1024 to 65535. - `headless` (boolean, optional, default false): Launch Chrome headless if debugger needs to be started. Permissions: Google Chrome ### chrome_list_sessions Category: Chrome CDP List active Chrome automation sessions. Arguments: No arguments. Permissions: Google Chrome ### chrome_navigate Category: Chrome CDP Navigate an active Chrome CDP session to a URL. Arguments: - `session_id` (string, required): Session returned by chrome_open_session. - `url` (string, required): URL to load. Permissions: Google Chrome ### chrome_wait_for Category: Chrome CDP Wait for a CSS selector in a Chrome CDP session. Arguments: - `session_id` (string, required): Session returned by chrome_open_session. - `selector` (string, required): CSS selector to wait for. - `timeout_ms` (integer, optional, default 10000): Maximum wait time in milliseconds. - `poll_ms` (integer, optional, default 200): Polling interval in milliseconds. Permissions: Google Chrome ### chrome_click Category: Chrome CDP Click an element in an active Chrome CDP session. Arguments: - `session_id` (string, required): Session returned by chrome_open_session. - `selector` (string, required): CSS selector for target element. Permissions: Google Chrome ### chrome_type Category: Chrome CDP Type text into an input element in an active Chrome CDP session. Arguments: - `session_id` (string, required): Session returned by chrome_open_session. - `selector` (string, required): CSS selector for target input. - `text` (string, required): Text to type. - `clear_first` (boolean, optional, default true): Clear existing value before typing. Permissions: Google Chrome ### chrome_extract Category: Chrome CDP Extract data by selector, attribute, or JavaScript expression. Arguments: - `session_id` (string, required): Session returned by chrome_open_session. - `selector` (string, optional): CSS selector to query. - `attribute` (string, optional): Attribute name to read from selected element. - `javascript_expression` (string, optional): JavaScript expression to evaluate. Permissions: Google Chrome ### chrome_screenshot Category: Chrome CDP Capture a screenshot of an active Chrome CDP session. Arguments: - `session_id` (string, required): Session returned by chrome_open_session. - `output_path` (string, optional): Optional output PNG path. Permissions: Google Chrome ### chrome_close_session Category: Chrome CDP Close a Chrome automation session. Arguments: - `session_id` (string, required): Session returned by chrome_open_session. Permissions: Google Chrome ### capture_active_screen Category: Screen Capture Capture a full screenshot of the display containing the frontmost app and return image output to the model. Arguments: - `output_path` (string, optional): Optional output PNG path. Permissions: Screen Recording ### add_screen_glow Category: Visual Feedback Add an orange screen-edge glow to show that automation is in progress. Arguments: No arguments. Permissions: Accessibility ### remove_screen_glow Category: Visual Feedback Remove the screen glow when automation completes. Arguments: No arguments. Permissions: Accessibility ## Example Workflows - Prompt: Find Sam in contacts and send an iMessage: Running 10 mins late. Tool path: search_contacts -> send_imessage - Prompt: Create tomorrow 9:30 AM standup in Work calendar for 30 minutes. Tool path: create_calendar_event - Prompt: Open a Chrome session, navigate to GitHub, wait for a selector, and extract page text. Tool path: chrome_open_session -> chrome_navigate -> chrome_wait_for -> chrome_extract - Prompt: Capture my active display and attach the screenshot for review. Tool path: capture_active_screen ## FAQ ### What is Altic MCP? Altic MCP is an open source Model Context Protocol server that lets MCP clients automate macOS apps and browser sessions. ### How many tools does Altic MCP expose? The README describes 20+ tools. The current server.py source exposes 37 exact MCP tools. ### Which automation areas are covered? Altic MCP covers Messages and Contacts, Notes and Reminders, Calendar, Safari, Chrome CDP, Screen Capture, System controls, and Visual Feedback. ### What is altic-studio? altic-studio is the shareable skill in the Altic MCP repo. It runs AppleScript automations via osascript and supports Messages, Contacts, Notes, Reminders, Calendar, Safari, system controls, screenshots, and Chrome CDP browser control. ### What are the requirements? Altic MCP requires macOS 10.13+, Python 3.13+, the UV package manager, and Google Chrome for Chrome CDP tools. ### What permissions are required? Contacts, Calendars, Reminders, Automation, Accessibility, and Screen Recording are required for the corresponding macOS integrations. Safari tools also require Safari's Allow JavaScript from Apple Events setting.