Speech-to-Text

A small Docker recipe for running Diction’s streaming gateway against Qwen3-ASR through Agent CLI, plus a test from a bar in the Netherlands, an ocean away from the GPU.

🎤 wyoming-mlx-whisper: Wyoming protocol server for near real-time Whisper speech-to-text on Apple Silicon, for use with Home Assistant voice or agent-cli. 🍏

My mostly self-hosted mobile development loop: WireGuard from an iPhone into my NixOS machine, persistent Blink/Mosh sessions, a systemd-managed agent-cli server, and an iOS Shortcut for FasterWhisper+Ollama dictation—paired with the best proprietary coding model available.

A personal journey of buying a gaming PC and accidentally falling down the rabbit hole of local, private AI. I share my experience building agent-cli and AIBrain, the tools I used, and the lessons I learned along the way.

🎙️ agent-cli: Local-first AI tools for your desktop: voice transcription to the clipboard with a hotkey, autocorrect, text-to-speech, RAG and memory proxies, and agent-cli dev for running coding agents in parallel Git worktrees. 🤖