OpenWhispr

OpenWhispr is a free, MIT-licensed dictation and meeting transcription app for people who want voice input across their apps with control over where processing happens. It's available on macOS, Windows, Linux and iOS. Local transcription works offline and keeps audio on your device; optional cloud transcription sends audio to the selected provider, whose retention policies apply.

You can dictate into apps such as Slack, Google Docs and Cursor, translate speech into another language, or ask an AI assistant to draft text and edit a selection. A custom dictionary learns names and technical terms from your corrections. Language detection also handles switches during speech.

On desktop, OpenWhispr detects Zoom, Teams and FaceTime calls, transcribes conversations, and labels speakers locally with recognition across meetings. It connects to Google, Microsoft and Apple calendars. Notes support folders, semantic search and AI actions, while audio and video imports let you transcribe existing recordings. Cloud sync and web sharing support shared notes and team spaces.

Desktop speech models include Whisper, NVIDIA Parakeet, Orukeet and Cohere Transcribe. AI reasoning and semantic search can also run locally, or you can use providers such as OpenAI, Claude and Gemini with your own API keys. On desktop, Whisper can use Apple Metal, NVIDIA CUDA or Vulkan for AMD and Intel GPUs. Intel Macs support meeting recording and transcription, but lack live speaker identification and voice fingerprinting; note searches use keyword matching.