[Release Notes]

Changelog

Newest releases first. Older releases follow below.

1.0.1

Added

  • Initial public release
  • Floating Windows dock with global hotkeys for dictation, AI commands, Ask Mode, and prompt-backed actions
  • Hands-free streaming dictation and instant Press & Hold capture modes
  • Windows system-sound capture via WASAPI loopback, alongside microphone device selection
  • Live transcription preview window with adjustable font size and auto-hide timing
  • Persistent recording history for dictation sessions and AI voice commands

Speech

  • Local STT engines: Parakeet V3, MedASR, Faster Whisper, and Kyutai Moshi
  • Cloud STT providers: AssemblyAI, Deepgram, Cartesia, Gradium, Gladia, Speechmatics, and Groq Whisper
  • Hot engine switching without restarting the app
  • Vocabulary correction with editable dictionaries and file-watch reloads
  • Dock waveform and bar visualizers driven by live RMS audio data

AI

  • AI provider support for OpenAI, Anthropic, Google, DeepSeek, OpenRouter, Cerebras, Groq, Alibaba, Zhipu, Perplexity, Mistral, MiniMax, and Moonshot
  • Local AI runtimes via Ollama and LM Studio
  • OpenAI OAuth sign-in for ChatGPT subscriptions, alongside standard API-key auth
  • AI Quick Lists for speed, intelligence, local models, and custom model shortcuts
  • AI Voice Command hold mode for spoken instructions over clipboard text or images
  • Provider-side web search through OpenAI OAuth/Codex and Perplexity
  • Image understanding for clipboard screenshots and photos with multimodal models
  • Image generation via Replicate, with results copied back to the clipboard
  • Rich AI Response Preview window with markdown, code highlighting, tables, math, and Mermaid diagrams

Workflow

  • Smart Actions with active prompt selection, dedicated action hotkeys, linked system info files, and per-prompt provider and model overrides
  • Smart Dictation on release, so Press & Hold transcripts can be rewritten before paste
  • Per-prompt AI Preview toggles for actions that should open the preview window automatically
  • Prompt and system-info libraries stored as editable text files, with live file watching and restore-default support
  • Bundled prompt pack covering rewriting, translation, email replies, image extraction, link cleanup, YouTube summaries, and vocabulary-term creation

Desktop

  • Dock mode with collapse and expand behavior, always-on-top control, top or bottom placement, and opacity settings
  • Theme customization with dark and light mode, curated backgrounds, accent colors, border-radius styles, and visualizer presets
  • Clipboard-preserving burst paste flow for dictation and AI output
  • Automatic updater delivery through Electron updater, Cloudflare R2, and the MachinesFluent Worker
  • GPU unload and reload controls for supported local models