FluidVoice is an open-source macOS dictation app that offers on-device speech-to-text (STT) and AI-enhanced transcription capabilities, providing a local alternative to cloud-based services.
Source: Description per README View on GitHub →FluidVoice is gaining attention due to its on-device AI enhancement model, which offers privacy and speed advantages over cloud-based dictation services. Its integration with multiple speech models and customizable features cater to a wide range of users, making it a compelling choice for those seeking a local dictation solution.
Source: Synthesis of README and project traitsA fully local AI model for on-device dictation enhancement, providing smart formatting, context-aware capitalization, and post-processing without sending data to the cloud.
Source: README Fluid Intelligence sectionVoice control for macOS, allowing users to launch apps, run shortcuts, and trigger system actions without touching the keyboard.
Source: README Features sectionDirect dictation into any text field across apps, with options to rewrite selected text or dictate new content inline.
Source: README Features sectionThe architecture of FluidVoice is inferred to be modular, with clear separation of concerns. It likely employs design patterns such as Model-View-Controller (MVC) for the user interface and Model-View-ViewModel (MVVM) for the data layer. The code tree suggests a focus on audio capture, speech recognition, and AI processing modules.
Source: Code tree + dependency filesCenter: project; inner ring: core feature modules; outer ring: key dependencies. Auto-generated from core_features and tech_stack.key_deps.
CoreAudioCaptureSupportSwiftUIFluidVoice is suitable for individuals and professionals who require hands-free dictation and transcription on macOS. It is useful for writers, speakers, and anyone who needs to convert spoken words into text quickly and securely, without relying on cloud services.
Source: READMEv1.6.2 (2026-07-06): Added custom dictionary learning from voice corrections.
Source: GitHub ReleasesFluidVoice is a promising project for developers and users seeking a fast, secure, and customizable dictation solution on macOS. Its focus on privacy and on-device AI enhancement positions it as a strong alternative to cloud-based dictation services, particularly for those who require high performance and data security.
FluidVoice is an open-source macOS dictation app that offers on-device speech-to-text (STT) and AI-enhanced transcription capabilities, providing a local alternative to cloud-based services.
FluidVoice's core features include: Fluid Intelligence, Command Mode, Write Mode.
FluidVoice is gaining attention due to its on-device AI enhancement model, which offers privacy and speed advantages over cloud-based dictation services.
FluidVoice is suitable for individuals and professionals who require hands-free dictation and transcription on macOS.