Speech To Markdown

Harness local AI for notes

Productivity

Writing

Artificial Intelligence

Visit WebsiteSee on Product Hunt

Fully local is the right tradeoff for notes-to-self — those are exactly the thoughts you don't want leaving the machine.

The part I'm curious about is the markdown side rather than the speech side. Spoken thinking is rambling and non-linear; markdown is structured. So something has to decide that this sentence is a heading and those three are a list, and I'd guess getting that wrong is more annoying than a plain transcription error. How much structure does it try to infer on its own versus waiting for me to say it out loud?

on-device is a smart default for something this personal. one thing I'd want to know before switching my note workflow over - does it handle mixed languages mid-recording ok, or does accuracy drop hard if you switch languages mid sentence like a lot of bilingual people actually talk?

fully local is the right call for something that's basically your unfiltered notes-to-self. curious what the hardware floor looks like though - does it bundle a specific small model sized for even an older/base-tier Mac, or does quality noticeably scale up on the higher-end Apple Silicon chips? asking because "local LLM" quality can vary a lot more by device than a cloud API would.

Local Whisper plus a local LLM into structured markdown is a strong privacy story for people who draft long notes or specs. The global hotkey for dictation in any text field is what I would actually use day to day. Curious which local model you recommend for heading and list structure without butchering technical terms, and whether users can pin a preferred outline style.

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.

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.