iOS & watchOS speech-to-text app with AI voice keyboard, on-device RAG, and chat with your notes - powered by Apple Foundation Models, WhisperKit, NVIDIA Parakeet, and 20+ AI providers
GitHub repository with 75 stars and 3 forks.
Language: Swift
Topics: asr, ios, speech-to-text, apple-foundation-model, watchos, rag
2026-06-05: 75 stars and 3 forks.
macOS menu bar app that tells you, in plain English, what each USB-C cable plugged into your Mac can actually do
GitHub repository with 5,461 stars and 169 forks.
Trending score: 4.04; stars gained: +203; forks gained: +3.
Language: Swift
Topics: apple-silicon, hardware-info, iokit, mac-app, macos, menubar
Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents
GitHub repository with 21,127 stars and 1,595 forks.
Trending score: 3.56; stars gained: +97; forks gained: +10.
Language: Swift
Topics: amp, claude-code, codex, gemini, ghostty, opencode
Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.
GitHub repository with 11,107 stars and 1,155 forks.
Trending score: 3.21; stars gained: +49; forks gained: +5.
Language: Swift
Topics: cpp, csharp, go, ios, java, lightweight
Move and resize windows on macOS with keyboard shortcuts and snap areas
GitHub repository with 29,176 stars and 939 forks.
Trending score: 2.27; stars gained: +31; forks gained: +3.
Language: Swift
让 AI 住在你 MacBook 的刘海里 · 零依赖开箱即用 · 多引擎并行的桌面 AI 伴侣（Swift 6 / SwiftUI / macOS 14+）
GitHub repository with 449 stars and 47 forks.
Trending score: 2.24; stars gained: +17; forks gained: +1.
Language: Swift
Topics: ai, chatgpt, chinese, claude, deepseek, desktop-app
OpenAI-compatible API proxy for Cursor Composer
GitHub repository with 166 stars and 24 forks.
Trending score: 2.07; stars gained: +10; forks gained: +1.
Language: Swift
Hold a key, speak, release — AI-polished text appears at your cursor in any app. Open-source voice input for macOS & Windows. (按住快捷键说话，松开即得润色后的文字)
GitHub repository with 2,150 stars and 169 forks.
Trending score: 2.75; stars gained: +25; forks gained: +1.
Language: HTML
Topics: ai-prompt, asr, dictation, linux, llm, macos
First foundation ASR built for the real world - 7 atomic acoustic conditions, 54 compound scenarios, 2.6M samples, and up to ~30% gains over SOTA where every other model falls apart. **You'll come back to MEGA-ASR, after the rest fail in the wild. ⭐**
GitHub repository with 957 stars and 61 forks.
Trending score: 2.72; stars gained: +33; forks gained: -1.
Language: Python
Topics: asr, robust
Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.
GitHub repository with 16,750 stars and 1,720 forks.
Trending score: 1.93; stars gained: +56; forks gained: +2.
Language: Python
Topics: pytorch, speech-recognition, paraformer, punctuation, speaker-diarization, voice-activity-detection
An end-to-end framework for multi-speaker transcription that jointly models who spoke, when, and what.
GitHub repository with 182 stars and 7 forks.
Trending score: 1.58; stars gained: +40; forks gained: +5.
Language: Python
Topics: asr, llm, sd, sdr, speech-recognition
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages
GitHub repository with 12,737 stars and 1,453 forks.
Trending score: 1.41; stars gained: +29; forks gained: +1.
Language: C++
Topics: asr, onnx, windows, linux, macos, cpp
Turn raw footage into brand-ready, platform-optimized video with one command. Local-first: FFmpeg + WhisperX/MLX + Ollama.
GitHub repository with 51 stars and 12 forks.
Trending score: 0.89; stars gained: +7; forks gained: +1.
Language: JavaScript
Topics: asr, captions, cli, ffmpeg, llm, local-first