Dabri provides offline speech-to-text dictation on Linux, with hotkeys, Whisper and Parakeet models, Vulkan acceleration and CLI control.
Read more
Dabri provides offline speech-to-text dictation on Linux, with hotkeys, Whisper and Parakeet models, Vulkan acceleration and CLI control.
Read more
Speech Note works with spoken and written material using local speech recognition, speech synthesis and machine translation.
Read more
aTrain is a graphical application to transcribe recorded speech while keeping source audio and resulting text on the user’s own computer.
Read more
faster-whisper is a reimplementation of OpenAI’s Whisper automatic speech recognition model built around CTranslate2
Read more
PocketSphinx is a compact, speaker-independent continuous speech recognition engine originating from CMU Sphinx.
Read more
whisper.cpp is a high-performance C/C++ implementation of OpenAI’s Whisper automatic speech recognition model.
Read more
Vocalinux provides private voice dictation with multiple speech engines, X11 and Wayland support, voice commands and GPU acceleration.
Read more
Handy provides offline desktop dictation with configurable shortcuts, local recognition models, transcription history and text insertion.
Read more
audapolis edits podcasts, interviews and other spoken-word media through locally generated transcripts, text selection and audio export.
Read more
AutoSubs generates local speech-to-text subtitles with speaker labels, translations and video editor integrations for common platforms.
Read more
ostt records and transcribes speech in the terminal using local or hosted models, with saved history and scriptable transcript processing.
Read more
hyprwhspr provides Linux dictation with local speech models, optional cloud services, configurable shortcuts and custom text corrections.
Read more
Whispering provides cross-platform speech dictation with global hotkeys, local or hosted transcription engines and automatic text insertion.
Read more
sherpa-onnx enables offline speech recognition, synthesis, speaker diarization, voice activity detection and audio processing.
Read more
WaveSurfer analyses and annotates speech recordings with waveform displays, spectrograms, transcription formats and plugins.
Read more
Simon provides configurable voice control of applications through user-defined speech models, scenarios and keyboard and mouse commands.
Read more
Eesen is to simplify the existing complicated, expertise-intensive ASR pipeline into a straightforward sequence learning problem.
Read more
CMUSphinx (Sphinx) is a collective term to describe a group of speech recognition systems developed at Carnegie Mellon University.
Read more
Julius provides a compact speech decoder with two-pass search, grammar recognition, real-time input and adaptable speech recognition models.
Read more
OpenSeq2Seq is a toolkit for distributed and mixed precision training of sequence-to-sequence models.
Read more