Release Notes
Version history for Flow Keyboard.
v0.2.34
- Bug fixes and improvements
v0.2.33
- Bug fixes and improvements
v0.2.32
- Improved the experience in weak network conditions
- Bug fixes and improvements
v0.2.31
- Improved stability, so Flow can keep up even in the most complex moments
- Improved history management, so your text and audio are easier to review, retry, or delete anytime
- Bug fixes and improvements
v0.2.30
- Bug fixes and improvements
v0.2.29
- Bug fixes and improvements
v0.2.28
- Bug fixes and improvements
v0.2.27
- Bug fixes and improvements
v0.2.26
- Added Traditional Chinese and Japanese app interface
- Bug fixes and improvements
v0.2.25
- Improved the keyboard typing experience
- Bug fixes and improvements
v0.2.24
- Smoother automatic voice input launch from the keyboard
- Improved typing efficiency for Pinyin and English keyboards
- Added punctuation preference settings
- Bug fixes and improvements
v0.2.23
- New Simplified Chinese Pinyin keyboard and English word suggestions, making it easier to correct, complete, and refine dictated text
- Bug fixes and improvements
v0.2.22
- Added bulk dictionary import
- Added dictation language variant preferences
- Bug fixes and improvements
v0.2.21
- Bug fixes and experience improvements
v0.2.20
- Fixed issues when phone is connected to CarPlay
- Bug fixes and improvements
v0.2.19
- Bug fixes and improvements
v0.2.18
- Bug fixes and experience improvements
v0.2.17
- Cross-device dictionary sync — your custom dictionary now syncs across signed-in devices
- Bug fixes and improvements
v0.2.16
- Bug fixes and improvements
v0.2.15
- Bug fixes and improvements
v0.2.14
- Bug fixes and improvements
v0.2.13
- Fixed keyboard switching issue on iPad and some devices
- Bug fixes and improvements
v0.2.12
- Bug fixes and improvements
v0.2.11
- Bug fixes and improvements
v0.2.10
- Dynamic Island & Lock Screen: see recording status at a glance while using other apps
- Bug fixes and improvements
v0.2.9
- Recording now continues even when the screen locks — no need to keep the screen on
- Bug fixes and improvements
v0.2.8
- Bug fixes and improvements
v0.2.7
- Bug fixes and improvements
v0.2.6
- Bug fixes and improvements
v0.2.5
- Editing mode now supports multi-step undo and redo
- Added line break and hyphen to the punctuation popup
- Bug fixes and improvements
v0.2.4
New Features
- Built-in QWERTY keyboard with letters, numbers & symbols — no need to switch input methods
- Add to Dictionary — long-press to select text in any app and save it to your personal dictionary
Improvements
- Auto-close timer now defaults to 5 minutes, with new 5-second and 1-minute options to reduce microphone indicator display time
- Faster voice recognition with lower latency
- Other fixes and improvements
Tip: After speech-to-text finishes, tap the Edit button in the bottom-right corner to refine the result — just say what you'd like to change.
v0.2.3
First Public ReleaseSpeak your thoughts naturally and get polished, professional text — no need to draft sentences or worry about grammar. Flow Keyboard is an AI voice typing keyboard that turns your speech into clear, structured writing in seconds.
AI-Powered Voice to Text
- Natural speech recognition that handles pauses, filler words, and incomplete sentences
- Automatic removal of verbal tics like "umm" and "uh"
- Built-in grammar correction, punctuation, and logical restructuring
Advanced Refinement
- Combines transcription with AI editing in a single step — processes messy spoken input into polished text without manual cleanup
Multilingual Support
- 30+ languages with automatic language detection
- Mixed Chinese/English recognition
- Translation mode — speak in one language, output in another (16 target languages)
System-Wide Keyboard
- Works across Messages, Mail, Notes, WeChat, Slack, and all other apps
- Requires iOS 17.0 or later
- 6.5 MB install size
Use Cases
- Quick message and email replies
- Report writing and meeting notes
- Brainstorming and voice-assisted coding prompts
Privacy
- Audio is processed and immediately discarded — zero server-side audio retention
v0.8.7
Public Beta- Improved shortcut settings: each shortcut group can now be disabled independently
- Improved selected-text voice editing: select text in an input field and let Flow revise it, or select web page content and ask Flow to explain or answer questions
- Improved stability under exceptional conditions, so you can use voice input without worrying about data loss
- Bug fixes and experience improvements
v0.8.6
Public Beta- App interface now available in more languages
- Improved dictation history management
- Bug fixes and improvements
v0.8.5
Public Beta- App interface now available in Japanese and Traditional Chinese
- Bug fixes and improvements
v0.8.4
Public Beta- Improved custom dictionary management, including bulk import
- Added language variant preferences for Traditional Chinese, Simplified Chinese, American English, and British English
- Bug fixes and experience improvements
v0.8.3
Public Beta- New option to automatically mute system audio while recording
- Bug fixes and improvements
v0.8.2
Public Beta- Bug fixes and improvements
v0.8.1
Public Beta- Dictionary sync — your custom dictionary now syncs across devices
- Bug fixes and improvements
v0.8.0
Public Beta- Bug fixes and improvements
v0.7.13
Public Beta- Bug fixes and improvements
v0.7.12
Public Beta- Bug fixes and improvements
v0.7.11
Public Beta- Improved recording stability when quickly restarting sessions
- Faster response in chat apps
- Bug fixes and improvements
v0.7.10
Public Beta- Bug fixes and improvements
v0.7.9
Public Beta- Bug fixes and improvements
v0.7.8
Public Beta- Bug fixes and improvements
v0.7.7
Public Beta- Bug fixes and improvements
v0.7.5
Public Beta- Bug fixes and improvements
v0.7.4
Public Beta- Bug fixes and improvements
v0.7.2
Public BetaAI Voice Input
- Speak naturally and get polished, well-structured text -- filler words removed, grammar fixed, punctuation added automatically
- 30+ language recognition with automatic mixed-language detection -- no manual switching needed
- Translation mode -- speak in one language, output text in another (16 target languages)
- Under 2 seconds for short recordings, up to 5 minutes maximum
Smart Output
- Vibe coding mode -- structures speech into clear prompts for AI coding tools (Claude Code, Codex, ChatGPT)
- Professional tone for workplace emails and documents
- Emotional tone preservation in casual chat (Slack, iMessage, Discord)
- Custom dictionary -- add proper nouns, brand names, and technical terms for higher accuracy
Edit Mode
- Select existing text and refine it with voice
Privacy & Performance
- Zero server-side data retention
- No surrounding text collection -- only your voice is sent to servers
- Native macOS app built with SwiftUI (< 30 MB installer)
- Works system-wide in any macOS app with a text field
v0.5.3
Internal Beta- The status bar now appears more promptly when pressing the recording shortcut
v0.5.2
Internal Beta- Fixed Windows status bar and popup buttons that could stop responding after the app was idle
v0.5.1
Internal Beta- Bug fixes and experience improvements
v0.5.0
Internal Beta- Improved long-recording and weak-network reliability, reducing cases where recording finishes without an input result
- Made it easier to recover results with Retry after canceling a long recording, canceling during processing, or a transcription failure
- Shows a Copy prompt when the text field loses focus or the current page is not editable, instead of ending silently
- Fixed some status bar and popup buttons that were visible but not clickable
- Refined the visual behavior of recording, translation, editing, and processing status bars to reduce obstruction and unusual deformation
- Edit mode now follows the selected punctuation style for more consistent output
- Added a voice-edit shortcut toggle in Settings, with per-shortcut controls
v0.4.0
Internal Beta- Raised the single recording limit to 10 minutes
- Improved stability
- Bug fixes and experience improvements
- Improved history
v0.3.1
Internal Beta- Bug fixes and improvements
v0.3.0
Internal Beta- Added Traditional Chinese, Japanese, and Korean interface languages
- Improved Windows shortcut handling, improving stability for single-key push-to-talk and combination shortcuts, and fixed shortcut conflicts
- Reduced latency for push-to-talk and selected-text editing
v0.2.3
Internal BetaImprovements
- Improved voice input network stability
- Improved shortcut settings (hands-free single-key trigger, shortcut recorder guidance)
Fixes
- Bug fixes and experience improvements
v0.2.1
Internal BetaImprovements
- Improved installer stability
- Refined overall UI
- Improved input speed
- Improved daily-use stability
New Features
- Magic Wand — edit and refine text with voice commands
- Auto-mute system audio during recording
- Bulk dictionary import
- Output preferences: language variants (Traditional Chinese, British English, etc.) and punctuation preferences
Fixes
- Fixed custom shortcut settings
v0.1.1
Internal Beta- Bug fixes and experience improvements
v0.1.0
Internal BetaInternal beta release of Flow Keyboard for Windows. This release brings Flow's core experience to Windows: use your voice instead of typing word by word, and turn thoughts into accurate, clear, ready-to-send text faster.
Faster Input
- Start recording with a global shortcut and type quickly in common Windows apps
- Speak naturally without drafting complete sentences in your head first
More Accurate, More Readable
- Handles pauses, filler words, and unfinished sentences while fixing grammar and adding punctuation
- Supports multilingual voice input and mixed Chinese-English use cases
- Supports a custom dictionary for names, brands, technical terms, and domain-specific words
Windows Desktop Experience
- Automatically insert results into the current text field, with copy fallback when direct insertion is unavailable
- Includes foundational pages for history, dictionary, settings, shortcuts, and account status
Privacy
- Zero server-side data retention
- No surrounding text collection by default -- only your voice input is processed
v0.3.0
Internal Beta- Android internal test update with input and voice experience improvements
- Other bug fixes and experience improvements
v0.2.5
Internal Beta- Improved notification and shortcut navigation after switching to Flow
- Bug fixes and experience improvements
v0.2.4
Internal Beta- Stability, update reminder, and interface experience improvements
v0.2.3
Internal Beta- Improved Bluetooth headset microphone support
- Fixed an occasional false "not signed in" prompt during voice input
- Bug fixes and experience improvements
v0.2.2
Internal BetaFirst Android internal test release of Flow Keyboard. This release brings Flow's core voice input experience to Android: speak naturally and turn thoughts into clear, ready-to-send text. Public download links are not available while the Android version is in internal testing.
AI Voice Input
- Speak naturally and get clear, polished text ready to send
- Handles pauses, filler words, and unfinished sentences while fixing grammar and adding punctuation
Voice Editing and Pinyin Correction
- After a recognition result appears, tap the magic wand to revise it with your voice
- Select text and replace it with a voice edit, or use pinyin to quickly fix individual words
Multilingual Support
- Supports multilingual voice input, mixed Chinese-English recognition, and translation mode
Android Input Experience
- Works in common Android app text fields, with history and custom dictionary support
Android remains invitation-only. Public download links are not available during internal testing; contact us if you need access.