[](https://github.com/royshil/obs-localvocal/releases)
LocalVocal live-streaming AI assistant plugin allows you to transcribe, locally on your machine, audio speech into text and perform various language processing functions on the text using AI / LLMs (Large Language Models). ✅ No GPU required, ✅ no cloud costs, ✅ no network and ✅ no downtime! Privacy first - all data stays on your machine.
Internally the plugin is running a neural network ([OpenAI Whisper](https://github.com/openai/whisper)) locally to predict in real time the speech and provide captions.
It's using the [Whisper.cpp](https://github.com/ggerganov/whisper.cpp) project from [ggerganov](https://github.com/ggerganov) to run the Whisper network in a very efficient way on CPUs and GPUs.
- [Background Removal](https://github.com/royshil/obs-backgroundremoval) removes background from webcam without a green screen.
- 🚧 Experimental 🚧 [CleanStream](https://github.com/royshil/obs-cleanstream) for real-time filler word (uh,um) and profanity removal from live audio stream
- [URL/API Source](https://github.com/royshil/obs-urlsource) that allows fetching live data from an API and displaying it in OBS.
Using the CI pipeline scripts, locally you would just call the zsh script. By default this builds a universal binary for both Intel and Apple Silicon. To build for a specific architecture please see `.github/scripts/.build.zsh` for the `-arch` options.
The above script should succeed and the plugin files (e.g. `obs-urlsource.plugin`) will reside in the `./release/Release` folder off of the root. Copy the `.plugin` file to the OBS directory e.g. `~/Library/Application Support/obs-studio/plugins`.
(Note that maybe the outputs will be in the `Release` folder and not the `install` folder like `pakage-macos` expects, so you will need to rename the folder from `build_x86_64/Release` to `build_x86_64/install`)
To build with CUDA support on Windows, you need to install the CUDA toolkit from NVIDIA. The CUDA toolkit is available for download from [here](https://developer.nvidia.com/cuda-downloads).
After installing the CUDA toolkit, you need to set variables to point CMake to the CUDA toolkit installation directory. For example, if you have installed the CUDA toolkit in `C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.4`, you need to set `CUDA_TOOLKIT_ROOT_DIR` to `C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.4` and `LOCALVOCAL_WITH_CUDA` to `ON` when running `.github/scripts/Build-Windows.ps1`.
You will need to copy a few CUDA .dll files to the location of the plugin .dll for it to run. The required .dll files from CUDA (which are located in the `bin` folder of the CUDA toolkit installation directory) are:
