Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Open Source project using LLMs to transcribe and translate subtitles (SRT, SSA/ASS, VTT)
| Date | Stars |
|---|---|
| 2026-08-03 | 634 |
| 2026-08-06 | 634 |
| 2026-08-12 | 636 |
| 2026-08-18 | 635 |
| 2026-08-19 | 636 |
| 2026-08-20 | 638 |
| 2026-08-21 | 640 |
| 2026-08-22 | 642 |
| 2026-08-23 | 643 |
| 2026-08-26 | 644 |
| 2026-08-28 | 643 |
| 2026-08-29 | 644 |
| 2026-08-30 | 645 |
| 2026-08-31 | 648 |
| 2026-09-02 | 649 |
| 2026-09-03 | 650 |
| 2026-09-05 | 650 |
| 2026-09-06 | 651 |
| 2026-09-09 | 651 |
| 2026-09-10 | 652 |
| 2026-09-11 | 653 |
| 2026-09-13 | 654 |
| 2026-09-16 | 655 |
| 2026-09-18 | 655 |
| 2026-09-22 | 655 |
| 2026-09-23 | 655 |
| 2026-09-24 | 655 |
| 2026-09-25 | 655 |
| 2026-09-26 | 655 |
| 2026-09-27 | 655 |
| 2026-09-28 | 656 |
| 2026-09-29 | 657 |
| 2026-10-01 | 657 |
| 2026-10-03 | 657 |
| 2026-10-04 | 657 |
| 2026-10-05 | 657 |
| 2026-10-07 | 658 |
| 2026-10-08 | 658 |
| 2026-10-12 | 658 |
| 2026-10-13 | 657 |
| 2026-10-14 | 659 |
| 2026-10-16 | 659 |
| 2026-10-17 | 661 |
| 2026-10-19 | 662 |
| 2026-10-20 | 662 |
| 2026-10-23 | 663 |
| 2026-10-26 | 662 |
| 2026-10-30 | 661 |
| 2026-11-01 | 662 |
| 2026-11-02 | 661 |
| 2026-11-03 | 662 |
| 2026-11-04 | 661 |
Today
-1 stars today
This week
-1 stars this week
This month
+4 stars this month
Momentum
60.0
growth rate 0.00%/day
# LLM-Subtrans LLM-Subtrans is an open source subtitle translator that uses LLMs as a translation service. It can translate subtitles between any language pairs supported by the language model. Supports multiple subtitle formats through a pluggable system (currently `.srt`, `.ssa`/`.ass` and `.vtt`). Provides transcription from video files and audio tracks, with speaker identification to improve translation accuracy, on supported models. **Note:** Subtitles and audio clips are sent to the provider's servers, so their privacy policy applies. ## Installation For most users the packaged release is the easiest way to use the program. Download a package from [the releases page](https://github.com/machinewrapped/llm-subtrans/releases), unzip to a folder and run `gui-subtrans`. You will be prompted for some basic settings on first run. If you want to use the command line tools, modify the code or just prefer to have more control over the setup you will need to [install from source](#installing-from-source). ### Windows Every release is packaged for Windows as (**gui-subtrans-x.x.x.zip**). ### MacOS Packaged builds are (usually) provided for MacOS with Apple Silicon (**gui-subtrans-x.x.x.macos-arm64.zip**). If you have an Intel Mac you will need to [install from source](#installing-from-source). ### Linux Prebuilt Linux packages are not provided so you will need to [install from source](#installing-from-source). ## Translation Providers ### Model providers #### Google Gemini https://ai.google.dev/terms Gemini Flash is probably the leading model for translation speed and fluency, despite some censorship. You will need a Google Gemini API key from https://ai.google.dev/ or from a project created on https://console.cloud.google.com/. You must ensure that Generative AI is enabled for the api key and project. Unfortunately Gemini will refuse to translate content that contains certain words or phrases, even with minimal safety settings. If you hit this you will need to use another provider for the batch. #### OpenAI https://openai.com/policies/privacy-policy You will need an OpenAI API key from https://platform.openai.com/account/api-keys to use OpenAI's GPT models. Alternatively, if you have an eligible ChatGPT plan you can tick **Use ChatGPT plan** in the provider settings and sign in with ChatGPT, so translation requests use your plan's usage allowance instead of a separately billed API key. Sign-in opens in your web browser. Usage is subject to your plan's limits, which you can manage in your [ChatGPT settings](https://chatgpt.com/settings/usage). This uses OpenAI's [Sign in with ChatGPT](https://developers.openai.com/siwc/token-sharing-open-source), which is currently in preview. It only covers translation: transcription with OpenAI still needs an API key. You can use the custom api_base parameter to access a custom OpenAI instance (or any other OpenAI-compatible endpoint, though the Custom Server option gives you more control). You can use an **OpenAI Azure** installation as a translation provider, but this is only advisable if you know what you're doing - in which case hopefully it will be clear how to configure the Azure provider settings. #### DeepSeek https://platform.deepseek.com/downloads/DeepSeek%20Open%20Platform%20Terms%20of%20Service.html You will need a DeepSeek API key from https://platform.deepseek.com/api_keys to use this provider. - **API Base**: You can optionally specify a custom URL, e.g. if you are hosting your own DeepSeek instance. DeepSeek is quite simple to set up and offers reasonable performance at a very low price, though translation does not seem to be its strongest point. #### Anthropic https://support.anthropic.com/en/collections/4078534-privacy-legal You will need an Anthropic API key from https://console.anthropic.com/settings/keys to use Claude as a provider. Translation is not Claude's strongest suit, and the API is expensive compared to others. The API has strict [rate limits
Excerpt of 38,176 characters
Read on GitHub
1.2k
4
4
Peter Dave Hello · @DNSCrypt @nodejs @maintainers @campus-experts @transmission-remote-gui · Taiwan
2
2
1
1
1
1
1
1
1
1
1
Aarish Alam · ScaledFocus · India
1
Thibault Jaigu
1
1
Albert Kaaman · Sweden
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:9940ab49dcabe948, llm:Description: 'Open Source project using LLMs to translate subtitles (SRT, SSA/ASS, VTT)'. Language: Python.
matched fp:9940ab49dcabe948, llm:Description: 'Open Source project using LLMs to translate subtitles (SRT, SSA/ASS, VTT)'. Language: Python.
matched fp:9940ab49dcabe948, llm:Description: 'Open Source project using LLMs to translate subtitles (SRT, SSA/ASS, VTT)'. Language: Python.