100% on-device, privacy first speech to text desktop app with offline Qwen grammar cleanup.
Cost / License
- Free
- Open Source (MIT)
Application type
Platforms
- Windows


Sonix is described as 'Converts audio and video into text, supports 35+ languages, and provides an in-browser editor for transcript management with automated subtitles' and is a audio transcription tool in the audio & music category. There are more than 100 alternatives to Sonix, not only websites but also apps for a variety of platforms, including Mac, Windows, iPhone and SaaS apps. The best Sonix alternative is Handy STT, which is both free and Open Source. Other great sites and apps similar to Sonix are Vibe Transcribe, Voxtral, FUTO Voice Input and TypeWhisper.
100% on-device, privacy first speech to text desktop app with offline Qwen grammar cleanup.




Kopia.ai is an AI transcription platform for audio and video files. It creates transcripts in minutes, includes a transcript editor synced to the source media for precise corrections, supports subtitle export and translation, and offers AI chat for summaries, analysis, and...


WordWand is a system-wide AI assistant for macOS that works in any app through a single keyboard shortcut. No copy-pasting, no tab switching — just select text, press a hotkey, and transform it instantly.



TimedSubs is a script-first subtitle timing tool for creators, editors, course producers, and localization teams.




koedesk is a cross-platform voice-to-text tool. Press and hold a key, speak naturally, and your words are typed straight into whatever app you're using — Claude, ChatGPT, Slack, Mail, your editor, anywhere you can type.




Free, open source voice dictation for macOS. On-device transcription with Apple's Speech framework. No cloud, no API keys, no account.



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.


Vocatim turns recorded or imported audio into editable transcripts on iPhone, iPad and Mac. It supports speaker labels and local AI summaries.



A lip reading web app that uses AI to analyze lip movements in videos and generate text transcripts. Designed for processing videos without needing sound, it works best with clear facial visibility.




Transcribe audio and video files in a blink, automatically, all offline, and with highly accurate results. AI Transcription uses OpenAI’s Whisper technology and Apple Speech Recognition to convert speech (like in podcasts, presentations, lectures, or voice messages) into text...




Bulbul is a free, open-source voice dictation app for Windows, macOS, Linux, and Android. Hold a hotkey (or tap the bubble on your phone), speak, and cleaned-up text appears in whatever app you're using — editor, browser, chat, terminal.