YouTube Transcript to Article

YouTube Transcript to Article is a self-hosted web app and HTTP API that converts YouTube captions into structured Markdown articles using an…

  • AI
  • Productivity
  • Tools & Utilities
YouTube Transcript to Article is a self-hosted web app and HTTP API that converts YouTube captions into structured Markdown articles using an OpenAI-compatible model. It resolves videos by URL or ID, supports depth levels and optional word targets, and lets users choose OpenAI or LocalAI for model calls. An optional MCP server mode returns only the transcript and video metadata so an external assistant can perform the writing. It is aimed at homelab users, writers, and researchers who want a controllable, API-driven way to turn spoken YouTube content into publishable text.

Platform availability

Available on 1 of 10 platforms

  • Unraid
  • TrueNAS (not listed)
  • Umbrel (not listed)
  • ZimaOS (not listed)
  • Proxmox (not listed)
  • Helm (not listed)
  • Mac (not listed)
  • Windows (not listed)
  • Linux (not listed)
  • Any server (not listed)

Health score?A 0-100 score computed nightly from four factors: maintained (40%: recent commits and steady activity), popular (25%: GitHub stars, log scale), easy to install (20%: platforms, install notes, setup guides, Docker image) and light to run (15%: minimum RAM, ARM support). When the source code has been checked, a fifth factor, security check (20%: automated scan for committed secrets, unsafe desktop-app settings, known-vulnerable dependencies and project hygiene; any serious finding caps it at 20), is added. Factors without data are left out and the rest are rescaled.

37/100 Low

Maintained
50last commit 226 days ago
Popular
187 GitHub stars
Easy to install
351 install platform, install notes, Docker image
Light to run
No data

Based on 3 of 4 factors.

Availability: platform listings confirmed today, links checked 27 days ago

GitHub stars
7
Open issues
1
Last commit
2026-04-09
License
MIT
Activity
stale

Checked 9 days ago - source: GitHub (patrickstigler/youtube-transcript-to-article)

Resources & Compatibility

ARM (e.g. Raspberry Pi) is not supported.

Checked 54 days ago - source: Docker Hub image tags and published docs

First-install notes

  • Install the YouTube API client Use Composer (the PHP package installer) or npm (the Node.js package installer) to add the Google API client to the app, such as composer require google/apiclient or npm install googleapis. Without it, the app has no YouTube API code to call and the setup will fail. source
  • Give YouTube an access token Set the API request to include your access token (the temporary login key) in the request's Authorization header or as the access_token parameter. Without it, YouTube will not accept the request. source
  • Container and model key Deploy patrickstigler/youtube-transcript-to-article from Docker Hub or GHCR; provide OPENAI_API_KEY for the web/API container unless running MCP-only mode. source
  • Model endpoint Configure the web/API container with an OpenAI-compatible endpoint, such as OpenAI or LocalAI, and set the default model or per-request model as needed. source

Fetched 39 days ago - each note links to its source

Alternatives

No alternatives collected yet.

Common questions

Can I use LocalAI instead of OpenAI?

Yes, the web app and HTTP API use an OpenAI-compatible chat model. OpenAI or LocalAI are supported.

Does MCP mode use an LLM inside the container?

No, optional MCP mode returns the transcript and video metadata only. It does not require an LLM in the container.

Can I adjust the article depth, length, language, or model?

Yes, the web/API can generate structured Markdown while you control depth, length, language, and model.

Can I pull the image from GitHub Container Registry?

Yes, the image is also available on GHCR. Set the repository to the GHCR repository and the registry to ghcr.io.

Answers sourced from github.com

Community

Collected 48 days ago - public community threads