Skip to content
SPECIFICTION
Get listed

GenSRT

github.com

Windows
Visit github.com
Spec score 7.3 #91 of 99 in AI Video Caption Generators

Spec sheet

Purpose
GenSRT is a GPU-accelerated subtitle generation and editing program that transcribes video into SRT subtitles.Read 12 Oct 2026 · github.com
Intended users
The maker describes the target users as content creators, fan subtitlers, accessibility teams, and researchers working with non-English media.Read 12 Oct 2026 · github.com
Platforms
The stated requirements are Windows 10 or Windows 11; it has CUDA and CPU builds, and also runs on Intel or AMD CPUs.Read 12 Oct 2026 · github.com
Free plan
YesRead 19 Sep 2026 · github.com
Integrations
SRT output supports filename suffixes compatible with Plex, Jellyfin, and Kodi.Read 12 Oct 2026 · github.com
Privacy
The project describes transcription and translation as running locally, and says its remaining translation engines work offline without a network dependency.Read 12 Oct 2026 · github.com
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.Read 12 Oct 2026 · github.com
Burn-in captions
YesRead 19 Sep 2026 · github.com
Connectivity requirement
An internet connection is needed to download models the first time they are used; the project says those downloads are one-time.Read 12 Oct 2026 · github.com
Editor and formats
The built-in player lets users add, split, merge, delete, and edit subtitle cues, and generation saves SRT and WebVTT files.Read 12 Oct 2026 · github.com
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.Read 12 Oct 2026 · github.com
Internet requirement
An internet connection is needed for the first-run download of speech-recognition or translation models.Read 12 Oct 2026 · github.com
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.Read 12 Oct 2026 · github.com
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.Read 12 Oct 2026 · github.com
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.Read 12 Oct 2026 · github.com
Output formats
Each generation writes SRT and WebVTT files, and the app can burn subtitles into a copy of the video.Read 12 Oct 2026 · github.com
Speech recognition
It supports OpenAI Whisper model sizes from tiny through large-v3-turbo and compatible Hugging Face faster-whisper models.Read 12 Oct 2026 · github.com
Subtitle editing
Its built-in player displays subtitles during playback and lets users add, split, merge, delete, and edit cues.Read 12 Oct 2026 · github.com
Subtitle export
srt and vttRead 19 Sep 2026 · github.com
Support and guidance
The executable ships with a self-contained HTML user guide covering the GUI workflow and command-line usage.Read 12 Oct 2026 · github.com
Supported platform
The stated system requirements are Windows 10 or Windows 11, with CUDA GPU acceleration or CPU operation.Read 12 Oct 2026 · github.com
Translation
It translates subtitles between languages offline using NLLB-200 or MADLAD-400, with no API, network dependency, or rate limits.Read 12 Oct 2026 · github.com
Translation license limit
The default NLLB-200 model weights are licensed CC-BY-NC-4.0 for non-commercial use; the maker identifies MADLAD-400 as an Apache-2.0 alternative suitable for commercial use.Read 12 Oct 2026 · github.com
Video tools
The feature list says GenSRT can burn subtitles into a video copy and includes ffmpeg, so no separate ffmpeg installation is required on target machines.Read 12 Oct 2026 · github.com

Where Specifiction places it

Alternatives to GenSRTAll alternatives →