obsidian-plugin/dsebastien_obsidian-transcriber

mirror of https://github.com/dsebastien/obsidian-transcriber.git synced 2026-07-22 07:02:24 +00:00

History

github-actions[bot] b93b4be5c9 chore(release): 1.4.1		2026-07-17 07:41:34 +00:00
..
_config.yml	chore(all): fixed obsidian review issues	2026-05-13 22:23:05 +02:00
configuration.md	docs(all): updated docs	2026-04-15 21:07:57 +02:00
README.md	docs(all): updated docs	2026-04-15 21:07:57 +02:00
release-notes.md	chore(release): 1.4.1	2026-07-17 07:41:34 +00:00
tips.md	docs(all): updated docs	2026-04-15 21:07:57 +02:00
usage.md	docs(all): updated docs	2026-04-15 21:07:57 +02:00

README.md

title	nav_order	permalink
Overview	1	/

Transcriber — User Guide

Transcriber converts images in your Obsidian vault to Markdown using Ollama vision models running locally on your machine. No data leaves your computer.

Key features

Transcribe individual images, entire folders, or all images embedded in a note
Output .md files are created alongside source images
Install, select, and remove AI models directly from the command palette — no terminal needed
Configurable vision model and transcription prompt
Progress notifications for batch operations
No cloud dependency — everything runs locally via Ollama

Prerequisites

Desktop Obsidian — this plugin is desktop-only (it requires a local Ollama server)
Ollama — installed and running on your machine

Quick start

Install the plugin from Settings > Community plugins and enable it
Ensure Ollama is running
Open Settings > Transcriber and click Test to verify the connection
Install a model: open the command palette (Ctrl/Cmd+P) and run Install AI model, or install from settings
Right-click an image in the file explorer and select Transcribe image

About