Speech-to-Markdown is a free, local-only app for macOS, iPhone, and iPad. If something isn't working, here's where to look and how to reach the developer directly.
Check that Speech-to-Markdown has Microphone access in System Settings → Privacy & Security (macOS) or Settings → Speech-to-Markdown (iOS).
Grant Accessibility access in System Settings → Privacy & Security → Accessibility, then restart the app — macOS only re-checks this permission on launch.
Agent Mode needs a local OpenAI-compatible server running (omlx, Ollama, LM Studio, or llama.cpp). Confirm the base URL in Settings… matches the port your server is listening on (default http://127.0.0.1:8000/v1).
Open Settings… from the menu bar and download a Whisper model — Base is a good starting point.
The iOS app requires an Apple Intelligence–capable device (iPhone 15 Pro or newer, or an Apple-Silicon iPad) on iOS 26+, with Apple Intelligence turned on in Settings.
Open an issue with details on your macOS/iOS version, device, and what you expected to happen — that's the fastest way to get a fix.