SyncPen — voice-to-Markdown pipeline for Obsidian

Talk while walking, and land a tidy Markdown note in your vault

Problem

Many people think best while walking, but phone typing lags behind thought. Voice memos solve the capture step yet create a new graveyard: a folder of recordings nobody reopens. Worse, recordings are trapped in the app's own library and can't drop into Obsidian or feed Claude Code.

Solution

A direct recording-to-Markdown pipeline: record on your phone, auto-detect language, transcribe, strip filler words, add punctuation, auto-title and summarize, classify by meeting/class/quick note, then write real .md files into a folder or Obsidian vault—never into a proprietary database.

Users

Obsidian and local-first note-takers, product/research people who think on the move, developers using Claude Code on their vault

MVP

Phone recording with language auto-detection; transcription, filler removal, punctuation; auto title and summary; type classification; export plain .md to a user folder or Obsidian vault with no lock-in.

Revenue

Free tier with a per-recording time cap; Pro subscription for longer recordings and more categories; or pay-per-hour transcription credits.

Why now

Local-first and the Obsidian ecosystem keep growing, and users increasingly want data in their own filesystem; piping voice transcription straight into the vault is a gap an indie dev can validate fast.