Morning
Morning is a macOS dictation app for people who want to turn speech into text wherever they can type. Hold a keyboard shortcut, speak, and release to paste the transcription at the cursor in apps such as email, notes, messaging tools, terminals, and coding assistants. Speech recognition runs locally on the Mac using Whisper models, and dictation can work offline after a model is downloaded. The app supports macOS 14 and later on Apple silicon and Intel Macs. It also places media controls and AirPods status in a notch-style interface, including on Macs without a physical notch. Optional AI text cleanup can be enabled separately and sends text to a selected provider. Morning offers unlimited dictation, a three-day free trial, and a one-time license purchase with lifetime updates; it is designed for Mac users, writers, developers, and other people who dictate into everyday apps.
Learn more about Morning
FluidVoice
FluidVoice is a free, open source macOS dictation app that pairs local speech recognition with Fluid-1, an on-device AI model for polishing dictation. One hotkey lets users speak into any text field across email, documents, chat, terminals, code editors, and other apps, with text appearing in near real time. Local speech models keep dictation on-device and work offline, while optional AI post-processing can use Fluid Intelligence, OpenAI, Groq, or custom providers. Fluid-1 cleans up rough dictation, fixes formatting, capitalization, dates, names, and numbers, and adapts tone to the active app without changing the speaker’s meaning. Users can create custom prompts for different apps, while Write Mode, Command Mode, and Direct Dictation make it easy to switch contexts. FluidVoice supports more than 40 languages across models including Nemotron Speech 3.5, Parakeet Flash, Parakeet TDT v2 and v3, Cohere Transcribe, Apple Speech, and Whisper.
Learn more about FluidVoice
StarWhisper
StarWhisper is free voice-to-text software for Windows that lets you dictate anywhere with AI-powered transcription. It works offline with local Whisper AI or connects to OpenAI for 99% accuracy. Features include 29+ languages, GPU acceleration, wake word activation, auto-paste, file transcription, and multiple AI models. A free tier (500 words/day) covers casual use, while Pro plans unlock unlimited transcription and all models.
Key Features:
- Offline transcription with local Whisper AI
- GPU acceleration for fast processing
- 29+ language support
- Wake word activation
- Auto-paste into any app
- File transcription
- Multiple AI model sizes
- OpenAI API integration
Use Cases:
- Dictate documents and emails
- Transcribe meeting recordings
- Voice-driven coding and notes
- Accessibility for users with mobility issues
- Multi-language content creation
Learn more about StarWhisper
Whisperstream
Whisperstream is a desktop dictation app for Windows PCs and Apple silicon Macs (beta) that converts speech into text for the focused field in other applications using a push-to-talk shortcut. After its speech-recognition models are downloaded, dictation can run locally and offline. Available models include NVIDIA Parakeet, Qwen3 ASR and Cohere Transcribe. Optional cleanup uses the on-device Stream-1 Mini model or a provider configured by the user. Features include custom vocabulary and text replacements, app-specific enhancement profiles, searchable transcript history, audio-file transcription, and voice playback and replies for Claude Code and Codex sessions. It supports dictation into compatible text fields without an add-in and is designed for people who want to speak into coding editors, email, documents and other applications. Model downloads, software updates and optional online functions may require internet access.
Learn more about Whisperstream