Rekody is described as 'Open-source, privacy-focused dictation runs locally on Mac, transcribing speech to text at your cursor in any app. No account, internet, or data leaves your device' and is a audio transcription tool in the audio & music category. There are more than 50 alternatives to Rekody for a variety of platforms, including Mac, Web-based, Windows, iPhone and Linux apps. The best Rekody alternative is Handy STT, which is both free and Open Source. Other great apps like Rekody are Vibe Transcribe, OpenWhispr, Voxtral and TypeWhisper.
Free open source speech-to-text app for desktop runs fully offline, keeping transcription and audio data private. Extensible and customizable, supports accessibility, cross-platform use, and community-driven modifications. No subscriptions or internet requirement.
Delivers offline transcription of audio and video using local AI for privacy, supports batch processing, multi-language input, real-time preview, multi-format export, English translation, direct printing, system audio, microphone input, CLI, and setup customization on Windows, Linux, or macOS.
Transforms spoken language into text using Whisper, supporting local and cloud AI, instant transcription, custom dictionaries, auto-paste, privacy-first local processing, cross-platform compatibility, Pro and free tiers, detailed history, and advanced customization options.
Advanced audio models for transcription, translation, and understanding, optimized for production and edge deployment, API accessible, open-source with Apache 2.0, delivering high accuracy, resource efficiency, and support for both large-scale and local use cases.
Runs privacy-focused speech-to-text locally on macOS, enabling system-wide dictation, batch audio and video file transcription, multi-engine support, drag-and-drop workflows, per-app profiles, searchable history, subtitle export with timestamps, and automation integration.
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.
Voice recognition software offering real-time transcription across any Mac app, instant customizable shortcuts, support for diverse accents, visual cues, privacy-focused with no hidden data collection, reduces manual typing, fully integrates for note taking, chat, or drafting.
Open-source desktop assistant enabling live dictation, customizable AI replies, language translation, screen-aware responses, chat panel, and on-device processing with full privacy controls. Works fully offline or with user-selected models. Hotkeys and settings customizable.
Linux desktop voice dictation tool enabling free, 100% offline transcription using whisper.cpp, OpenAI Whisper, or VOSK engines. Offers GPU acceleration on AMD, NVIDIA, Intel, supports X11 and Wayland, real-time text entry, system tray integration, and secure operation.
An open-source, end-to-end speech recognition system trained on 680,000 hours of diverse audio, providing multilingual transcription, to-English translation, language identification, phrase-level timestamps, and high performance in real-world scenarios using transformer architecture.
Local macOS solution for fast AI-powered transcription and translation of audio or video in over 100 languages, featuring speaker diarization, batch processing, GPU acceleration, file-type flexibility, drag-and-drop support, advanced editing, and secure privacy.
United States
Israel
France
EU
Germany
Kazakhstan
Nepal
New Zealand
