On the recordRead 12 Oct 202624 facts
GenSRT
On the record
- Burn-in captions
- Yesgithub.com · read 19 Sep 2026
- Connectivity requirement
- An internet connection is needed to download models the first time they are used; the project says those downloads are one-time.github.com · read 12 Oct 2026
- Editor and formats
- The built-in player lets users add, split, merge, delete, and edit subtitle cues, and generation saves SRT and WebVTT files.github.com · read 12 Oct 2026
- Installers
- The download instructions offer an NVIDIA GPU installer and a smaller CPU-only installer that runs on Intel or AMD systems and integrated graphics.github.com · read 12 Oct 2026
- Integrations
- SRT output supports filename suffixes compatible with Plex, Jellyfin, and Kodi.github.com · read 12 Oct 2026
- Intended users
- The maker describes the target users as content creators, fan subtitlers, accessibility teams, and researchers working with non-English media.github.com · read 12 Oct 2026
- Internet requirement
- An internet connection is needed for the first-run download of speech-recognition or translation models.github.com · read 12 Oct 2026
- Known limitation
- Fine-tuned Whisper models can emit very short spurious subtitle cues at chunk boundaries, which users may need to delete in the editor.github.com · read 12 Oct 2026
- Known limitations
- The README reports that fine-tuned Whisper models can produce very short spurious cues, monolingual models can render other-language passages phonetically, and built-in models can struggle with fast, dense Indian-language speech.github.com · read 12 Oct 2026
- License
- GenSRT is licensed under GNU AGPL version 3.0, and the maker says to contact the maintainer about commercial licensing options such as proprietary integration.github.com · read 12 Oct 2026
- Model license limit
- The NLLB-200 model weights are CC-BY-NC-4.0 for non-commercial use, while the README identifies MADLAD-400 as Apache-2.0 and suitable for commercial use.github.com · read 12 Oct 2026
- Output formats
- Each generation writes SRT and WebVTT files, and the app can burn subtitles into a copy of the video.github.com · read 12 Oct 2026
- Privacy
- The project describes transcription and translation as running locally, and says its remaining translation engines work offline without a network dependency.github.com · read 12 Oct 2026
- Purpose
- GenSRT is a GPU-accelerated subtitle generation and editing program that transcribes video into SRT subtitles.github.com · read 12 Oct 2026
- Speech recognition
- It supports OpenAI Whisper model sizes from tiny through large-v3-turbo and compatible Hugging Face faster-whisper models.github.com · read 12 Oct 2026
- Subtitle editing
- Its built-in player displays subtitles during playback and lets users add, split, merge, delete, and edit cues.github.com · read 12 Oct 2026
- Subtitle export
- srt and vttgithub.com · read 19 Sep 2026
- Support and guidance
- The executable ships with a self-contained HTML user guide covering the GUI workflow and command-line usage.github.com · read 12 Oct 2026
