Transcriber converts images in your Obsidian vault to Markdown using Ollama vision models running locally on your machine.
Latest release 2.1.1 · 28 Sept 2026
3 files for Claude Code, Codex and OpenCode: obsidian-transcriber, obsidian-transcriber AGENTS.md, obsidian-transcriber CLAUDE.md — 9,042 tokens loaded in every session.
AGENTS.md A 9,035 tok CLAUDE.md A 7 tok .claude/settings.json A — These files are dsebastien/obsidian-transcriber's own configuration — they tell Claude Code, Codex and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.