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
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
Spokenly
Spokenly is an AI-powered dictation app for Mac, iPhone, Windows, and Linux that turns speech into clean, punctuated text wherever you work. Hold a shortcut, speak naturally, and release to place the transcription directly at the cursor in browsers, email, chat, word processors, IDEs, terminals, and other apps. It supports more than 100 languages, including mixed-language dictation, and offers both local and cloud speech-to-text models. Whisper, Parakeet, and other on-device models can run completely offline, while cloud engines from providers such as OpenAI, Deepgram, Groq, Soniox, and ElevenLabs can be used for higher-accuracy or real-time transcription. Local Only Mode blocks network requests so voice data stays on the device. Modes let users save different transcription models, AI providers, prompts, and output styles for specific tasks, while AI Instructions can remove filler words, fix grammar and punctuation, summarize, rewrite, translate, or reformat dictated text.
Learn more about Spokenly
MacWhisper
MacWhisper is an all-in-one Mac transcription app for transcribing files, meetings, lectures, podcasts, videos, subtitles, voice memos, and private recordings. The app lets users drag and drop audio or video files, record online meetings, capture app audio, and use real-time dictation in any app. MacWhisper supports Zoom, Teams, Webex, Skype, Discord, and other meeting platforms without requiring bots to join calls. Its local AI models help users transcribe sensitive files offline so data does not have to leave the Mac. The platform includes speaker recognition, filler-word removal, translation, transcript search, editing, batch transcription, exports, summaries, chat, and custom AI prompts. Built for professionals, students, creators, researchers, journalists, and privacy-conscious users, MacWhisper helps turn speech and media into clean, searchable, editable text.
Learn more about MacWhisper