Epilude Narrator

BetterVoice is an experimental, open-source macOS menu-bar app for local voice dictation with screen context. It transcribes speech locally and captures the full display whenever the user circles an area with the pointer, marking each capture with a blue pointer trail and pulse while preserving multiple references in order. The app inserts the transcript into the selected text field when macOS permits it and pastes captured images when both speech and screen context are available. It supports quick notes and long explanations, configurable microphones, dictation languages, circle-detection thresholds, and keyboard shortcuts. English uses a local Parakeet model by default, while other languages use a separately downloaded multilingual model; an optional English-only grammar-cleanup feature runs locally through quantized ONNX weights.

BetterWispr is a free, open-source, local-first voice-dictation app for macOS. It uses Apple on-device speech recognition, NVIDIA Parakeet, or Whisper to transcribe speech locally and paste the result into the active application; built-in models work offline after download. It supports hold-to-talk or toggle shortcuts, vocabulary and phrase replacements, voice commands, correction learning, and locally stored transcript history. Its meeting mode provides live transcripts, titles, summaries, and action items using Apple Intelligence or a local Ollama model. Optional Sarvam AI, Smallest AI, and OpenAI-compatible endpoints can be added, in which case audio is sent to the selected endpoint rather than handled entirely on-device. The project requires macOS 14 or later, recommends Apple Silicon, and is distributed under the Apache-2.0 license.

Lipflow is an open-source, cross-platform silent lip-reading dictation tool that uses a webcam to turn mouthed words into text pasted at the cursor. It runs locally on macOS, Windows, and Linux: face landmarks are tracked live, 96×96 grayscale mouth crops are sampled at 25 fps, and an Auto-AVSR visual-speech-recognition pipeline combines a 3D-convolutional ResNet front end, Conformer encoder, Transformer decoder, CTC scoring, and a subword language model with beam search. Users can train the language model and lip reader on their phrasing and face, import local Wispr Flow dictation history, and optionally apply cleanup through offline rules, an on-device Qwen model, Claude, Codex CLI, or Ollama. Whisper mode combines lip and audio input with an audio-visual model while the hotkey is held. The repository is MIT-licensed, although its LRS3-trained model weights are identified as for non-commercial research use.

Qwen Scribe is a private, local transcription and system-wide dictation application for Apple Silicon Macs. It runs Qwen3-ASR through mlx-qwen3-asr on the Mac's Metal GPU, keeping audio and transcripts on the computer without an account, API key, or cloud service. Users can drag audio or video into a local web interface, transcribe with automatic or forced language selection, vocabulary hints, word timestamps, and SRT export, and search or export local transcript history. A menu-bar helper provides push-to-talk dictation in text fields, displaying listening and transcription states in a non-focus-stealing HUD before pasting the result at the cursor. The project requires macOS 14 or newer, Apple Silicon, Python 3.12 or newer, and ffmpeg for non-WAV audio and video. It offers Qwen3-ASR 1.7B and 0.6B model options; model weights are downloaded separately and require roughly 3.4 GB or 1.2 GB of unified memory respectively, in addition to application overhead. It is distributed as a downloadable beta Mac app or can be built from source; the repository describes the project as version 0.2.1-beta.1.