A free, open source, and extensible speech-to-text application that works completely offline.



Dictly is described as 'Turns speech into polished, structured text — instantly and entirely on your device. No servers. No data collection. No delay' and is a audio transcription tool in the audio & music category. There are more than 50 alternatives to Dictly for a variety of platforms, including Mac, Web-based, Windows, Linux and Android apps. The best Dictly alternative is Handy STT, which is both free and Open Source. Other great apps like Dictly are Vibe Transcribe, Voxtral, FUTO Voice Input and Whisper.
A free, open source, and extensible speech-to-text application that works completely offline.



Vibe is an auto transcription service that utilizes local language learning models (LLMs) or artificial intelligence to provide transcriptions for a wide range of languages. The service prioritizes user privacy by offering fully offline transcription, ensuring that no data ever...

Voxtral models are state-of-the-art speech understanding models, which are available in two sizes — a 24B variant for production-scale applications and a 3B variant for local and edge deployments. Both versions are released under the Apache 2.0 license.

FUTO Voice Input is an application that lets you do speech-to-text on Android, integrating with third party keyboards or apps that use the generic speech-to-text APIs.



Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.




TranscribeX is a powerful macOS app that converts your audio and video into accurate transcripts, translates them into over 100 languages, and helps you summarize or edit with advanced AI tools. Built with OpenAI Whisper and Nvidia Parakeet models, TranscribeX delivers accuracy...




TalkNotes turns audio into structured notes, todos, flashcards, and transcripts using AI transcription in 100+ languages. Automatically capture lectures, meetings, or any speech into actionable text, ensuring tasks never get lost, with user-friendly accessibility for everyone.








Moonshine is a family of speech-to-text models optimized for fast and accurate automatic speech recognition (ASR) on resource-constrained devices. It is well-suited to real-time, on-device applications like live transcription and voice command recognition.
Transcribe audio and video files automagically with simple drag-and-drop — even in batches! Be amazed by remarkable accuracy and rapid results.




Instantly converts spoken words to text using local AI for near-perfect accuracy and privacy, with real-time transcription, seamless macOS integration, user-supplied AI keys, multiple language support, and no cloud data upload required.




Privacy-focused transcription tool for macOS. For free. No ads, no tracking, no data collection.

