Faster Whisper
Faster Whisper transcription with CTranslate2
subsai is an open-source local llm project by absadiki (absadiki/subsai on GitHub). It has 1,679 GitHub stars and 135 forks, is released under the GPL-3.0 license, and was last updated on GitHub on 20 April 2026.
Whisper-powered subtitle generation: Web UI, CLI, and package.
Via pip or from source.
Web UI, CLI, or Python API.
Audio or video files go in.
Timed subtitle files come out.
State-of-the-art transcription.
Web UI, CLI, and Python package.
Choose speed versus accuracy.
Proper subtitle timing.
Guides for every interface.
Open source, share-alike.
Add SubsAI via pip.
pip install subsaiSee the available options.
subsai --helpRun it on a media file.
subsai run -m video.mp4A Whisper-powered subtitle generator with Web UI, CLI, and Python package, at absadiki/subsai.
Whisper and its variants; pick per speed and accuracy needs.
The source is open under GPL-3.0.
It helps; CPU works for smaller models.
On the GitHub Pages docs site.
Faster Whisper transcription with CTranslate2
Auto-subtitle videos with AI transcription, translation and voice cloning
Blazing-fast multi-backend Whisper transcription for any file or URL.
Noise-robust subtitle generator powered by Whisper and local ASR models.
Early proposal and implementation for connecting LLMs to web pages.
Private AI chat and model studio that runs in your browser via WebGPU.
The most-starred other Local LLM projects in the LibreAI catalogue — the realistic shortlist if subsai is not the right fit.
The simplest way to run open language models on your own machine.
User-friendly AI Interface (Supports Ollama, OpenAI API, ...)
LLM inference in C/C++
A high-throughput and memory-efficient inference and serving engine for LLMs
🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.
Nearby Local LLM projects in the catalogue, closest in stars to subsai — keep exploring the shelf either side of it.
AI OSINT agent with 20 tools and REPL — for authorized research only.
Self-evolving general AI agent running fully locally, a Manus-style alternative.
OLMo-core — the current PyTorch building blocks for the OLMo open language model ecosystem, Apache-2.0
Agent hub that spins up a fresh orchestrator per task, local-first.
AI file organizer that sorts and renames files by understanding content.
Lightweight inference engine for running LLMs efficiently on any device.
Free and open — grab the source, star the repo, and start creating.