ChatterKey v4.5.0 — One model. One request.

ChatterKey v4.5.0 — One model. One request.

Released September 8, 2026 · macOS 14+ · Apple Silicon download · Build 8

ChatterKey now uses one configurable audio-capable model for every dictation and voice-edit attempt, defaulting to Gemini 3.5 Flash-Lite through OpenRouter. Speak, release, and receive the final text without a separate transcription or polishing stage.

What's changed

• A single audio request in all eight writing modes: same-language cleanup, English translation, professional, casual, concise, bullets, technical, and verbatim.
• Magic Voice Edit in one request: selected text and the spoken instruction audio are sent together; the model returns the replacement text directly.
• No hidden follow-up requests: removed separate Whisper/GPT transcription, second-stage polishing, English-compliance repair, automatic network retries, and automatic provider fallback routing. Retry is an explicit user action.
• One model field in Settings: choose another audio-input/text-output model in the future without adding another processing stage. Update its cost rates when switching.
• OpenRouter-only active connection: one fixed official endpoint and one provider key. Legacy provider identities remain readable in historical usage records.
• Updated onboarding and documentation: the README, website, architecture overview, privacy/security disclosures, and downloads now describe the single-model workflow.

Fixes and safeguards

• Translation and other writing modes still apply when optional smart cleanup is disabled.
• Added a clipboard-copy fallback for selection detection when standard Accessibility attributes are unavailable. This improves compatibility with browsers, Electron apps, PDFs, Notes, and editors; support still depends on the target app.
• Synthetic selection-copy events are ignored by the push-to-talk event handler.
• Empty, blocked, and truncated model responses are rejected instead of inserting incomplete output.
• Verbatim output no longer expands local snippet cues or spoken formatting phrases.
• Voice-edit output bypasses local snippet and formatting transformations so the selected document is not inadvertently expanded.
• Processing requests are pinned to OpenRouter, HTTP redirects are rejected, and legacy-provider configurations cannot send credentials through the new client.

Costs and migration

• Cost estimates now include audio tokens + instruction/selected-text tokens + output tokens, not a separate per-minute transcription charge.
• The rough on-device preview is not counted as an additional text input; voice-edit selections are counted.
• Legacy settings and usage records migrate to the single-model format, preserving writing preferences, vocabulary, snippets, and local history preferences. Existing OpenRouter Gemini model selections are retained.
• Previous OpenAI/custom or text-only configurations move to the Gemini default and require an OpenRouter API key. Keys stay in their original Keychain accounts and are never copied between providers.
• Estimates are approximate, not invoices. Additional reasoning, failed requests, explicit retries, taxes, and platform fees are excluded. Review rates when changing models or when provider pricing changes.

Requirements and installation

1. macOS 14 or later on an Apple Silicon Mac for the downloadable binary.
2. Your own OpenRouter API key; Gemini 3.5 Flash-Lite is selected by default.
3. Microphone and Accessibility permissions. Speech Recognition remains optional for the on-device live preview, which does not add a cloud model request.
4. Quit the old app, extract ChatterKey-v4.5.0.zip, replace the app in Applications, and launch it. Review the migrated model and rates in Settings.

Distribution warning: This is an ad-hoc signed community-test build, not Developer ID signed or Apple-notarized. It has not been validated on a clean Mac account. Gatekeeper may block it. Do not disable system-wide security protections to install it. The ZIP is arm64, not a universal Intel/Apple Silicon binary.

The accompanying ChatterKey-v4.5.0.zip.sha256 verifies download integrity; a checksum is not Apple approval or a publisher identity guarantee. After downloading both files into the same directory:

shasum -a 256 -c ChatterKey-v4.5.0.zip.sha256

Validation and known limits

• Swift 6 model/endpoint regression harness covers all writing modes with cleanup on/off, request contents/counts, voice edits, migration, cost estimates, invalid responses, cancellation, and failure paths.
• Debug and release builds, public-source checks, signature verification, and release-archive checksum checks are part of this release's validation.
• Single-request behaviour is verified with mock transport tests; this release does not claim measured real-provider latency, transcription accuracy, or universal cross-app compatibility.
• Switching to another model requires audio-input and text-output support. A text-only model cannot replace Gemini in this pipeline.
• No automatic translation repair means an imperfect model result is returned without a hidden second call. Review important output before using it.

Short announcement

ChatterKey v4.5.0 is here: one model, one request. Gemini 3.5 Flash-Lite now handles dictation, translation, verbatim, and voice edits directly from audio. This release removes separate transcription/polishing stages and hidden retries, improves text-selection handling, simplifies Settings, and updates cost estimates to audio-plus-text token pricing. Your local preferences migrate, and provider keys remain isolated. Available as an Apple Silicon community-test build; not Apple-notarized.

ChatterKey v0.4.0

ChatterKey v0.4.0

This release brings transparency, local productivity insights, and a cleaner way to manage dictation history.

What’s new

• Local usage dashboard with words spoken, speaking time, average WPM, daily activity, and provider breakdowns
• Whole-process cost estimates covering transcription and optional AI polishing
• Speaking insights for repeated phrases, filler words, and overly long thoughts
• Custom AI system instructions with an exact generated-prompt preview
• Unified Dashboard and History pages inside the Settings window
• Complete local dictation history with copy, reinsert, retention, and clear actions
• Editable cost rates for transcription and input/output tokens
• Cleaner menu-bar popover showing only the latest dictation with Copy and View More

Privacy

Dashboard analytics are local. ChatterKey stores aggregate usage metadata—not transcript text or audio—for cost and productivity insights. API keys remain in macOS Keychain.

Requirements

• macOS 14 or later
• Microphone and Accessibility permissions
• Optional Speech Recognition permission for live preview
• Your own provider API key

The downloadable app is ad-hoc signed for community testing. macOS may require confirming the app in Privacy & Security.

ChatterKey v0.3.1

What’s new

• New ChatterKey application icon across macOS, GitHub, and the product website.
• Privacy-safe starter vocabulary for common technology names.
• Three editable, general-purpose voice snippets.

Reliability fixes

• Restored compact 16 kHz mono PCM uploads while preserving live transcription preview.
• Added isolated provider sessions, transient-network retry, and bounded processing timeouts.
• Added automatic dedicated speech-to-text fallback when OpenRouter single-pass processing times out or loses its connection.
• Failure overlays now dismiss automatically while keeping recorded audio available for Retry.

Installation

Download ChatterKey-v0.3.1.zip, unzip it, and move ChatterKey.app to Applications. This build is ad-hoc signed for open-source distribution and is not notarized.

ChatterKey v0.3.0 — Live Transcription & Magic Voice Edit

ChatterKey v0.3.0

This release makes voice typing feel immediate and adds spoken editing for text that already exists.

Added

• Live Transcription: see an on-device rough transcript inside the floating ChatterKey pill while speaking.
• Magic Voice Edit: select text, hold the shortcut, and speak an instruction to rewrite, shorten, translate, or reformat it in place.
• Live Preview Controls: enable or disable live transcription from Settings.
• Speech Recognition Setup: permission status and diagnostics are now included in onboarding and Settings.

Improved

• The compact waveform smoothly expands into a live transcript pill and returns to the small completion state after insertion.
• Selected text is detected through macOS Accessibility without reading secure text fields.
• Privacy documentation now explains selected-text processing and the optional on-device preview.

Fixed

• Fixed real-time audio callback isolation crashes when push-to-talk started.
• Fixed Speech Recognition authorization and partial-result callback crashes.

Installation

1. Download ChatterKey-v0.3.0.zip below.
2. Extract the archive and move ChatterKey.app to Applications.
3. Replace the previous version when prompted.
4. Allow Microphone, Accessibility, and optional Speech Recognition access.
5. If macOS asks for Keychain access after replacing a local build, enter your Mac login password and choose Always Allow.

This direct build is ad-hoc signed and is not yet notarized by Apple. macOS may require approval from Privacy & Security on first launch.

ChatterKey v0.2.4 — Voice Productivity & Modern Settings

ChatterKey v0.2.4

This release adds voice productivity tools and a fully redesigned Settings experience while improving clipboard safety and sidebar responsiveness.

Added

• Voice Snippets: expand short spoken cues into exact reusable text after transcription.
• Spoken Formatting Commands: support new lines, paragraphs, bullet points, and punctuation with English and common Hinglish phrases.
• Modern Settings UI: new macOS-style sidebar, focused detail pages, reusable cards, empty states, and a persistent save footer.

Improved

• Settings window is now resizable with clearer navigation and better spacing.
• Provider, vocabulary, snippets, diagnostics, shortcut, and history controls are organized into dedicated pages.
• Snippet content is expanded locally after transcription.
• Sidebar changes are immediate, with unnecessary section transition animations disabled.

Fixed

• Removed the stale keyboard-focus border that remained on a previously selected sidebar item.
• Clipboard restoration now preserves multiple pasteboard item types.
• ChatterKey no longer overwrites content copied by the user immediately after dictation.
• Original clipboard content is restored if automatic paste setup fails.

Installation

1. Download ChatterKey-v0.2.4.zip below.
2. Extract the archive and move ChatterKey.app to Applications.
3. Replace the previous ChatterKey version when prompted.
4. Open Settings to configure voice snippets and spoken formatting commands.

This direct build is ad-hoc signed and is not yet notarized by Apple. macOS may require approval from Privacy & Security on first launch.

ChatterKey v0.2.1 — Compact Overlay Fix

ChatterKey v0.2.1

A focused bug-fix release that makes the dictation overlay smaller, cleaner, and less distracting.

Changed

• Replaced the large dictation status pill with a compact animation-only indicator.
• Listening now displays only an animated audio waveform.
• Processing uses a small animated-dot indicator.
• Successful insertion displays a compact green check animation.
• Failure displays a small warning indicator.
• Kept failed-dictation retry available from the menu-bar popover.

Fixed

• Removed the rectangular macOS window shadow around the compact indicator.
• Removed the clipped gray border/background visible outside the black rounded overlay.
• Made the overlay ignore mouse events so it does not block interaction with the active app.

Installation

1. Download ChatterKey-v0.2.1.zip below.
2. Extract it and move ChatterKey.app to Applications.
3. Replace the previous ChatterKey version when prompted.

This direct build is ad-hoc signed and is not yet notarized by Apple. macOS may require approval from Privacy & Security on first launch.

ChatterKey v0.2.0

ChatterKey v0.2.0

A major usability update focused on onboarding, customization, reliability, and a smoother everyday dictation workflow.

Added

• Guided first-run onboarding and permission setup.
• Diagnostics for microphone, Accessibility, shortcut, Keychain, and provider connectivity.
• Eight output modes: same language, English translation, professional, casual, concise, bullet points, technical, and verbatim.
• Personal dictionary for names, products, acronyms, and preferred spellings.
• Optional local transcript history with retention controls.
• Copy and reinsert actions for recent transcripts.
• Retry failed dictation without recording again.
• Configurable shortcuts: Fn, Right Option, Option-Space, and Command-Shift-Space.
• Quick output-mode switching from the menu-bar popover.

Improved

• Redesigned menu-bar popover and Settings experience.
• Better AI instructions for Hinglish, translation, cleanup, and personal vocabulary.
• More reliable settings and API-key persistence.

Fixed

• Prevented repeated unexpected Keychain password prompts caused by older local-build credentials.
• Changed Keychain saving to update-or-create instead of delete-and-recreate.
• Preserved temporary audio after processing failures so users can retry safely.

Privacy

• Transcript history is disabled by default and remains local when enabled.
• Audio is never stored in transcript history.
• API keys remain in macOS Keychain.

Installation

1. Download ChatterKey-v0.2.0.zip below.
2. Extract it and move ChatterKey.app to Applications.
3. Open ChatterKey and complete the setup guide.
4. Enter your provider API key once in the v0.2 provider setup.

This build is ad-hoc signed for direct distribution and is not yet notarized by Apple. macOS may require approval from Privacy & Security on first launch.

ChatterKey v0.1.0

ChatterKey v0.1.0

The initial public release of ChatterKey, a native AI voice-typing utility for macOS.

Highlights

• Hold Fn to record and release to transcribe.
• Native SwiftUI menu-bar experience with a floating microphone overlay.
• Automatic text insertion into the focused macOS application.
• OpenAI, OpenRouter, and custom OpenAI-compatible provider support.
• Hinglish and Hindi cleanup with optional English translation.
• Editable transcription and polishing model IDs.
• API keys stored in macOS Keychain.
• No analytics, advertising, account requirement, or hard-coded credentials.

Requirements

• macOS 14 or later
• Microphone and Accessibility permissions
• Your own supported provider API key