Hold a key, speak, release — AI voice-to-text dictation that types into any Windows app. Free & open-source.
Cost / License
- Free
- Open Source (GPL-3.0)
Platforms
- Windows



Moonshine AI is described as 'On-device speech recognition tool with real-time transcription, command recognition, speaker identification, low word-error rates, and multi-language support' and is a audio transcription tool in the ai tools & services category. There are more than 100 alternatives to Moonshine AI for a variety of platforms, including Mac, Web-based, Windows, iPhone and iPad apps. The best Moonshine AI alternative is Handy STT, which is both free and Open Source. Other great apps like Moonshine AI are Vibe Transcribe, Voxtral, FUTO Voice Input and TypeWhisper.
Hold a key, speak, release — AI voice-to-text dictation that types into any Windows app. Free & open-source.



FLUENT is a hotkey-activated speech-to-text recognition tool that conveniently displays the recognition results & copies them to the clipboard.




Voice dictation that stays on your device. Open-source, local-first, and built for people who actually care about privacy.




Hold-to-talk speech-to-text for macOS. 100% local, powered by WhisperKit and local LLM cleanup. Hold Control to record, release to transcribe and paste.
Wave is a lightweight, native macOS dictation app focused on fast voice-to-text workflows with minimal UI overhead. Press a shortcut, speak, and your words are instantly pasted at the cursor. Supports on-device transcription via Whisper and cloud transcription via Groq, plus an...



Transcribes video speech into subtitles using advanced AI models with multilingual translation, live subtitle editing and preview, robust quality checks, support for offline processing, customizable exports as SRT, ASS, or burnt-in, suitable for creators and professionals.



SaidVault is a privacy-first macOS transcription app that runs locally on Apple Silicon. It transcribes audio and video files, records voice notes, captures system audio for meetings or video playback, supports Whisper and Parakeet models, and exports to PDF, TXT, Markdown, SRT, and VTT.


Offline hold-to-talk voice dictation and transcription for the desktop. Hold a key, speak, release — the text is typed into the focused app. Speech recognition runs locally after setup and model download, so no cloud account, API key, GPU or subscription is needed.



Cadence is a native voice workspace. Because our AI model runs on-device, your voice never leaves your Mac.




Transcriboar is a lightweight Android transcription app that uses the device’s built-in SpeechRecognizer to convert speech to text in real time.



NotchLive is a macOS menu bar app that displays real-time AI-powered captions and translations directly in your MacBook's notch. It uses on-device Whisper AI (via CoreML) for speech recognition and Apple Translation for real-time translation — nothing ever leaves your Mac.

