Offline Speech-to-Text and Transcription

SpeechPulse is a dictation and transcription app for people who want to write by voice or turn recordings into text. Its Whisper speech recognition runs locally, so dictation can work without an internet connection.

Volyx Lens is an open-source desktop AI assistant for macOS, Windows and Linux that lets you choose which screen, microphone and system-audio inputs reach your AI provider. Linux support is experimental, with meeting audio captured on a best-effort basis. It's for people who want help with visible code, documents or meetings without continually copying context into a chat. A movable floating rail expands into chat and collapses when you don't need it.

insanely-fast-whisper is a command-line audio transcription tool for people who want to process recordings on their own hardware. It focuses on reducing transcription time through GPU acceleration.

WhisperX is a local speech-to-text tool for transcribing interviews, meetings and long recordings. It builds on OpenAI's Whisper, adding individual word timings and optional speaker identification for subtitles and transcript review.

DoodleNote turns calls and rough jottings into meeting notes for people who want to keep recordings on their own computer. It captures both sides of a conversation in any meeting app without adding a bot to the participant list.

AudioBud is a dictation app for Windows that puts speech into the text field you're writing in. It builds on Handy by CJ Pais and suits people who want voice typing with local speech recognition rather than a hosted transcription service.

Voxtral Small is an audio and text model for developers building self-hosted speech applications. The separate mistral-inference library is archived and no longer maintained; this model runs with vLLM or Hugging Face Transformers.