OpenWhispr

whisper.cpp is a C/C++ implementation of OpenAI's Whisper automatic speech-recognition model for speech-to-text inference. It is designed for offline, on-device use and supports CPU-only inference, GPU and NPU acceleration, integer quantization, mixed F16/F32 precision, voice activity detection, and a C-style API. The implementation targets macOS, iOS, Android, Linux, Windows, WebAssembly, Raspberry Pi, Docker, and other platforms, with optimizations including ARM NEON, Apple's Accelerate and Metal frameworks, x86 AVX, POWER VSX, Vulkan, CUDA-related NVIDIA support, ROCm, OpenVINO, and other backends. The repository includes the whisper-cli example, which transcribes 16-bit WAV audio using Whisper models converted to ggml format; its zero-dependency implementation is intended for integration into applications such as on-device captioning tools.

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.

Steno is an open-source, privacy-first desktop AI notepad and meeting notetaker for Windows and macOS, intended for confidential conversations. It records microphone and system audio, provides live or post-meeting transcription with speaker labels, generates summaries, and supports natural-language queries across individual notes or the meeting library. Its local mode uses on-device AI models; on Apple Silicon, live transcription uses Parakeet TDT v3 through MLX, while Whisper supports post-stop transcription in 99 languages. On macOS 14.4 and later, native Core Audio Tap captures both sides of virtual meetings without a virtual audio cable and with selectable microphone input. Steno can detect meeting start and end events, offer to start or summarize recordings, append recordings to existing notes, provide global recording shortcuts, and include user notes in generated summaries. Notes, transcripts, and summaries are stored as editable Markdown, with one-way synchronization to an Obsidian vault and report templates for structured outputs. The project states that local recordings, transcripts, and summaries remain on the device and have no cloud usage limits; users can alternatively configure hosted models through OpenAI, Anthropic, AWS Bedrock, or a custom API endpoint.

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.