Apple Dictation
Apple Dictation is a built-in macOS feature that lets users speak to enter text anywhere they can type. Once Dictation is enabled, it can be started with the Microphone key, a customizable keyboard shortcut, or Start Dictation, then stopped with Escape, the same shortcut, or the Microphone key. On Apple silicon Macs, users can continue typing while they dictate, and Dictation resumes listening after keyboard input stops. Spoken commands can insert emoji, punctuation, new lines, and new paragraphs, while supported languages can automatically add commas, periods, and question marks. Dictation supports text of any length and stops automatically after 30 seconds without detected speech. When macOS is uncertain about a word, it underlines the text so users can choose an alternative or correct it manually. Multiple Dictation languages can be enabled and switched while speaking, and users can select a preferred microphone or let macOS choose automatically.
Learn more
Aiko
Aiko is an AI-powered audio transcription app for macOS, iOS, and visionOS. The app converts speech to text from meetings, lectures, recordings, and other audio files using OpenAI’s Whisper model running locally on the user’s device. Aiko is designed for high-quality on-device transcription, making it useful for sensitive recordings that should remain private. The app supports Shortcuts, allowing users to build workflows for recording, transcribing, copying, saving, or processing transcripts. It is available as a Universal Purchase across supported Apple platforms. Built for Apple users who need private speech-to-text, Aiko helps turn audio into text without sending recordings to cloud transcription services.
Learn more
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
DictaFlow
DictaFlow is an AI dictation app for Windows, Mac, iPhone, and Android via Telegram that turns messy speech into clean text wherever the cursor is. Hold a keyboard shortcut, mouse button, or VDI-safe trigger, speak naturally, and release to insert text directly into email, documents, IDEs, EHRs, browsers, terminals, notes, and remote desktops. It is built for the messy parts of dictation, including names, acronyms, code terms, drug names, clinical shorthand, contract language, accents, and more than 100 languages. DictaFlow understands mid-sentence corrections such as “actually” and “I mean,” so users can fix mistakes without breaking rhythm, and AI cleanup can turn rough speech into emails, bullets, code comments, meeting notes, prompts, or formatted text as they talk. Users can also highlight existing text in apps such as Word, Slack, or VS Code and edit it by voice.
Learn more
