pluja/anysub

★ 3,105⑂ 185

Turn audio and video into subtitles with an easy-to-use web UI. Everything runs on your own machine.

About pluja/anysub

pluja/anysub is an open-source project on GitHub, mainly written in TypeScript. Turn audio and video into subtitles with an easy-to-use web UI. Everything runs on your own machine. It currently holds 3,105 stars and 185 forks with 23 open issues, and was last pushed on 2026-11-13 (repository created 2023-08-26).

Project Overview

Git Homed tracks it on the Audio Trending board and on the AI Audio Trending list.

GitHub Repository Details

Repository pluja/anysub · default branch main · size 17631 KB · watchers 34 · source: GitHub REST API and repository README

README

https://github.com/pluja/anysub/blob/HEAD/

Anysub

Anysub (formerly Whishper) makes subtitles from audio and video. Upload a recording, let Whisper transcribe it, then fix the text and timing in the editor and export. It runs on your own computer or server.

https://github.com/pluja/anysub/blob/HEAD/The Anysub studio with the video, the subtitle list and the waveform timeline

Features

Install

You need Linux on x86-64 with Docker and Docker Compose.

1. Create a folder and download the Compose file:

   mkdir anysub && cd anysub
   curl -fsSLO https://github.com/pluja/anysub/releases/latest/download/compose.yaml
   

2. Optional. Skip to step 3 to transcribe on the CPU. Otherwise, download one extra file into the same folder and turn it on:

     curl -fsSLO https://github.com/pluja/anysub/releases/latest/download/compose.cuda.yaml
     echo "COMPOSE_FILE=compose.yaml:compose.cuda.yaml" >> .env
     
     curl -fsSLO https://github.com/pluja/anysub/releases/latest/download/compose.remote.yaml
     echo "COMPOSE_FILE=compose.yaml:compose.remote.yaml" >> .env
     

3. Start Anysub:

   docker compose up -d
   

4. Open http://localhost:5173 and create your account. It asks for a setup code, which docker compose logs web shows.

A GPU transcribes several times faster than a CPU. AMD and Intel GPUs aren't supported yet, but we plan to add them.

Install covers Podman, reverse proxies and building from source. NVIDIA GPUs helps when the GPU doesn't work.

Coming from Whishper 3

Whishper 3 is no longer maintained, and Anysub can't read its data. Coming from Whishper 3 explains how to move over. The old code is in the v3-legacy branch.

Not built yet

These will come in 4.x releases. See the changelog.

Documentation

See docs.

AI disclosure

Large language models helped write the code and docs. A human reviews and tests every change before it ships.

License

AGPL-3.0-only.

GitHub Stars & Activity

3,105Stars
185Forks
23Open issues
TypeScriptLanguage

GitHub Popularity

GitHub stars3,105
Forks185
Open issues23
Primary languageTypeScript
LicenseAGPL-3.0
Stars gained today0
Created2023-08-26
Last pushed2026-11-13

Trending History

Trending statusnot on today's boards

Related GitHub Projects

1

TalAter / annyang

TypeScript★ 6,821⑂ 0
→
2

liuzhao1225 / YouDub-webui

TypeScript★ 5,861⑂ 0
→
3

rsxdalv / TTS-WebUI

TypeScript★ 3,314⑂ 0
→
4

timoncool / YuE2-Studio

TypeScript★ 2,287⑂ 0
→
5

leemysw / yovoice

TypeScript★ 2,231⑂ 0
→
6

react-native-voice / voice

TypeScript★ 2,161⑂ 0
→
7

huggingface / transformers

Python★ 169,134⑂ 0
→
8

debpalash / VoiceStudio

Python★ 112,289⑂ 0
→

More Trending Repositories