GitHub - iannuttall/natter: Fast, local-first dictation for macOSkept by eddie • aug 13Natter is a macOS menu bar app that performs local, offline dictation with cleanup for technical terms and voice-taught corrections.AboutMLX · Parakeet · Natter · QwenFiled#ai-coding#developer-tools#macos#open-source#productivityRelatedAsk HN: What's the current best local/open speech-to-speech setup?Developers find that truly local, low-latency speech-to-speech AI is not yet achievable with end-to-end open models, so the best 2026 setups combine streaming ASR, LLM, and TTS on a single GPU using frameworks like Pipecat.also on Parakeet, #open-source, #developer-toolsThe PR you would have opened yourselfHugging Face built a Claude Code Skill and test harness that helps contributors port language models from transformers to mlx-lm while preserving code quality and reviewer trust.also on MLX, #open-source, #ai-coding, #developer-toolsRunning local models is good nowLocal agentic coding models have reached surprising quality and usability over the past six months, now offering ~75% of frontier-model accuracy for many development tasks on a 64GB M2 Mac.also on Qwen, #open-source, #ai-coding, #productivity, #developer-tools9 theses on AI | Sarthak MunshiAI progress is constrained by long-task reliability, labor reallocation, cost inefficiencies of general APIs, the declining value of raw coding skills, inadequate benchmark testing, the limits of formal verification without strong specs, memory-bound local hardware advantages, the shift from data to environment-driven training, and the rising competitiveness of US open-weight models.also on Qwen, #open-source, #ai-coding, #developer-tools
GitHub - iannuttall/natter: Fast, local-first dictation for macOS