Home/Developer Tools/obs-localvocal
obs-localvocal logo

obs-localvocal

Enrichment pending
royshil/obs-localvocal

OBS plugin for local speech recognition and captioning using AI

GraphCanon updated today · GitHub synced today

1.5k
Stars
120
Forks
52
Open issues
14
Watchers
1mo
Last push
C++ GPL-2.0Created Aug 10, 2023

Trust & integrity

Full report
Maintenance
Steady (52d since push)
As of today · Source: github_public_v1
Provenance
Not a fork · Personal account
As of today · Source: github_public_v1
Security (OSV)
No lockfile
As of today · Source: none

Public GitHub metadata and optional OSV dependency scans. Signals, not a guarantee. Trust methodology.

Overview

OBS plugin for local speech recognition and captioning using AI

Capability facts

Languages
c++

Source: github.language · Jul 11, 2026

Categories

Tags

README

Repo sponsors: Recall.ai - API for desktop recording

If you’re looking for a hosted desktop recording API, consider checking out Recall.ai, an API that records Zoom, Google Meet, Microsoft Teams, in-person meetings, and more.

LocalVocal - Speech AI assistant OBS Plugin


Downloads

Windows

OSGeneric (x86_64)NVidia (x86_64)AMD (x86_64)
Windows 10/11-0078d6?style=for-the-badge&logo=windows&logoColor=white)-0078d6?style=for-the-badge&logo=windows&logoColor=white)-0078d6?style=for-the-badge&logo=windows&logoColor=white)

Linux

OSGeneric (x86_64)NVidia (x86_64)AMD (x86_64)
Ubuntu 22.04 (Jammy) .deb-FCC624?style=for-the-badge&logo=linux&logoColor=black)-FCC624?style=for-the-badge&logo=linux&logoColor=black)-FCC624?style=for-the-badge&logo=linux&logoColor=black)

MacOS

MacOSIntel x86_64ARM64 (Apple silicon - M1/M2/M3/M4)
Generic*
12 (Monterey)
13 (Ventura)
14 (Sonoma)
15 (Sequoia)

*While variants for specific versions of MacOS may work better on that version of MacOS, the Generic variant is likely the best option. See MacOS Variants below for more details

Check out the latest releases for downloads and install instructions.

Introduction

LocalVocal lets you transcribe, locally on your machine, speech into text and simultaneously translate to any language. ✅ No GPU required, ✅ no cloud costs, ✅ no network and ✅ no downtime! Privacy first - all data stays on your machine.

The plugin runs OpenAI's Whisper to process real-time speech and predict a transcription, utilizing Whisper.cpp from ggerganov to run the model efficiently on CPUs and GPUs. Translation is done with CTranslate2.

Usage

Badge image   Badge image   Badge image
https://youtu.be/ns4cP9HFTxQ https://youtu.be/4llyfNi9FGs https://youtu.be/R04w02qG26o

Do more with LocalVocal: