Audio and video · Independent · 22 Oct 2026

McCloudS/subgen

Autogenerate subtitles using OpenAI Whisper Model via Jellyfin, Plex, Emby, Tautulli, or Bazarr

← Audio and video
Subgen: AI subtitle generator. Creates subtitles for media files using local AI.

In simple English

This tool listens to your movies and TV shows, and then writes subtitle files for them. It runs completely on your own computer or server, so nothing is sent to an outside company. You can connect it to media servers like Plex or Jellyfin so it makes subtitles the moment new media arrives. It can also work with Bazarr to supply missing subtitles automatically. It costs nothing in subscription fees, but needs a computer with enough memory to run an artificial intelligence model.

What it is

Subgen is a self-hosted (running on your own hardware rather than a rented cloud service) application that turns spoken words into subtitle files using the Whisper speech recognition model. It listens for webhooks (automated notification messages sent between web services) from popular media managers or exposes an API (a way for different programs to talk to each other) for subtitle applications.

What it is good for

This is useful for solo builders and home server enthusiasts who want accurate subtitles for media files that lack them, without paying for cloud transcription services.

Stars1.5k
LicenceMIT
LatestNo tagged releasechecked 22 Oct 2026
Last code change2026-08-07
Written inPython
Setup effort
3 / 5
Payoff
4 / 5
Good
  • Runs entirely on your own hardware with no cloud fees or data sharing.
  • Integrates directly with Bazarr, Plex, Jellyfin, Emby, and Tautulli.
  • Supports both CPU processing and Nvidia GPU acceleration for faster results.
Watch for
  • Requires Docker and some technical knowledge to configure environment variables.
  • Artificial intelligence transcription needs a significant amount of memory or video RAM to run well.
  • Mistranslations or hallucinations can occasionally happen due to background noise in audio tracks.
Replaces

manually downloading subtitles or paying for cloud transcription APIs

Works well with

Bazarr

Similar repositories
  • ahmetoner/whisper-asr-webservice3.4k stars

    Another self-hosted Whisper transcription service with an API, but lacking the deep media server webhook integrations of Subgen.

  • openai/whisper111k stars

    The underlying speech recognition model created by OpenAI, which requires writing custom scripts rather than using a ready-made media server companion.

Also reviewed on Repo Radar
  • snapcast/snapcast8.0k stars

    A server and clients that play one audio stream in several rooms, kept in time with each other.

  • MusicPlayerDaemon/MPD2.8k stars

    A background music player with no interface of its own, controlled over a network by separate client programs.

  • AcademySoftwareFoundation/OpenTimelineIO2.0k stars

    An interchange format and library for editing timelines: the order and length of cuts, and references to the media, but not the media.

Install
docker run -d \
  --name subgen \
  -p 9000:9000 \
  -e TRANSCRIBE_DEVICE=cpu \
  mccloud/subgen:latest

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: Design & Creative › Video Creation & Editing › Captions & Subtitles.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.