#3333rd of 50 in Data and scraping for AIFor image, video and design, video and animation
subtitle-translator
Browser-based batch subtitle translator for SRT, ASS, VTT and LRC files
- Stars
- 1.2k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Sep 2026
- Language
- TypeScript
826 on 21 Apr 20261,197 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Parses .srt, .ass, .vtt and .lrc files locally, strips timecodes and headers, and sends only dialogue text to one of 8 machine-translation APIs or 27 LLM providers and gateways. It handles whole seasons in batch, multiple target languages per pass, and bilingual output including two-style ASS. A `yarn cli` command runs the same engine headlessly, and it can be self-hosted with Node.js 24 or newer.
Who it is for: Users translating subtitle files in bulk, in browser or CLI
Strengths
- Timecodes and cue numbers never reach the model, so timing cannot be rewritten
- Free GTX and Edge engines work with no key or setup
- Local models work through any OpenAI-compatible URL, e.g. Ollama at localhost:11434
- CLI shares engine and cache with the web app, and runs resume after interruption
Weaknesses
- Complex inline ASS effect tags are simplified during translation
- Context mode with models under 70B parameters may produce misaligned output
- CORS-blocked providers go through a relay, built-in or self-deployed Worker
- Free GTX and Edge engines are rate-limited and rated lower for stability
What it needs
- no GPU
- Docker
- Needs Node.js >= 24, Yarn
- Models: DeepL, Google Translate, Azure Translate, DeepLX, Qwen-MT
- port 3000
Quick answers
Is subtitle-translator open source?
Yes. Its code is on GitHub under the MIT license.
Can you run subtitle-translator with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does subtitle-translator need a GPU?
No, it runs without one.
Also in Data and scraping for AI
See all 50| Rank | Project | Score |
|---|---|---|
| 1 | doclingPython library that converts PDFs, Office files and more into structured text | 92 out of 100 |
| 2 | mineruParses PDFs, images and Office files into Markdown and structured JSON | 91 out of 100 |
| 3 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 90 out of 100 |
| #4 | agent-reachCLI that gives coding agents read access to login-gated and Chinese web platforms | 88 out of 100 |
| #5 | markitdownPython library and CLI that converts office files, PDFs and audio to Markdown | 87 out of 100 |