Speech To Markdown
Harness local AI for notes
Start new thread

Speech To Markdown - Harness local AI for notes

by•
A free macOS and iOS app that turns your voice into structured markdown using local LLM. Global dictation anywhere with ⌘⌥], live markdown editor with on-the-fly fix with LLM. No cloud, no API keys — nothing leaves your Mac.

Add a comment

Replies

Best
Maker
📌

Out of all the prototypes I've built to leverage local LLMs, the one I actually ended up using daily is my Speech-to-Markdown (STMD). Your speech goes through Local Whisper (STT) ➡️ gets processed by a local LLM ➡️ and is finally converted into a structured spec ✅

Using Fable, I finally managed to turn it from a web app into a native Mac app 💻, and I've been using it even more since. Whenever I have a new idea, I just open the app and start talking. My product ideas backlog has never been longer; now I just need more time (and more tokens 🤑).

🔗 |

🎙️ The very first idea I "talked" into it was a Dictation mode for STMD — finally giving a purpose to the custom buttons on my keyboard ⌨️. Just focus on any text field, press a hotkey, and start talking. You can use it with or without an LLM to automatically fix grammar and typos.

📱 I also published an iOS version leveraging Apple Intelligence, but somehow it didn't click ( 🍎). I guess most of my ideas come while I'm already sitting at my laptop.

looks useful. i'd also spend more time on the design. right now it feels a bit too ai-generated. i'd make it feel more human and give it a stronger visual identity.

also, why would i switch from wispr flow, superwhisper, or macwhisper? i'd make that value prop much clearer on the landing page.

Whisper running locally handles clean, single speaker English reasonably well, but the real test for a dictation tool is messy speech, false starts, self corrections, "wait, scratch that," switching languages mid sentence, background noise from wherever the idea struck. Since ideas apparently strike constantly for you given the backlog comment, how does STMD handle you correcting yourself out loud, does the local LLM catch that you meant to replace the previous sentence rather than append to it, or does a correction just get written into the structured spec as if it were additional content. Also, the dictation mode fixing grammar and typos on the fly in any text field is the feature I'd actually reach for daily, more than the full spec generation. Does that grammar correction run per sentence as you pause, or does it wait until you stop dictating entirely, since correcting too aggressively mid thought could end up rewriting something you hadn't finished saying yet.