OnKey

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.

Tonefold is a free, open-source AI music composer for macOS and Windows. It turns plain-language requests into editable song layers—including chords, melody, bass, drums, pads, arpeggios, plucks, counter-melody, harmony, sub, and percussion—in a piano roll with note, velocity, and drum-lane editing. Its built-in General MIDI synthesizer provides playback, and it exports MIDI, a stereo WAV mix, and separate WAV stems. In Producer mode, an agent reads the session and proposes a plan specifying the key, tempo, form, layers, and sections to change. The app enforces approval before writing; four specialists then work on their assigned layers, after which the producer checks the host's recorded ledger and can revert the whole run. Composer mode supports quick changes without the multi-step plan. The native Rust desktop app handles the piano roll, playback, approval gate, and run ledger. A Node.js sidecar using the Claude Agent SDK communicates with it over a local WebSocket. Chat can use the user's Claude login through Claude Code or an Ollama model on the local network, while generation, playback, editing, and export run on the user's machine. Optional CLAP and VST3 plugins provide DAW integration, and a CLI and skill file allow Claude Code or Codex to compose. Tonefold is distributed under GPL-3.0.

Sonar is an experimental macOS app by Emanuel Perez that uses a Mac’s built-in speakers and microphone for camera-free hand-gesture control. It plays a steady high-frequency tone, typically 20 kHz, analyzes Doppler shifts in echoes reflected from the user’s hand, and maps detected movement to scrolling, swiping, and zoom commands. It includes calibration, practice demos, signal visualization, diagnostics, and support for other applications; microphone audio is processed locally in memory and discarded after processing. Sonar requires macOS 14 or later, supports Apple silicon downloads, and is distributed under the MIT license.

VoiceStudio is an open-source, fully local desktop application for voice cloning and design, text-to-speech, transcription, dictation, video dubbing, and long-form audio production. It runs on macOS Apple Silicon, Windows, Linux, or Docker and keeps voices, projects, settings, and generated files on the machine by default. The application combines a Tauri desktop shell, a React and Vite interface, and a local FastAPI backend with registries for multiple TTS and ASR engines. Its workflows can transcribe and translate video, preserve speaker assignments, synthesize replacement speech, render audiobook chapters, separate vocals, diarize speakers, process batch jobs, and route work to CPU, CUDA, Apple Silicon MPS/MLX, ROCm, or optional remote workers. It also exposes local REST, SSE, WebSocket, OpenAI-compatible audio, and MCP interfaces, including speech synthesis and transcription endpoints. VoiceStudio is licensed under AGPL-3.0; downloaded models and tokenizers retain their own licenses. The local workflow requires no account, API key, subscription, or usage meter, although remote workers, configured external ASR endpoints, analytics, and other network-backed functions are opt-in. The repository describes the software as an active beta and distributes packaged desktop releases as well as source code.