# royshil/obs-localvocal

OBS plugin for local speech recognition and captioning using AI

Repository: https://github.com/royshil/obs-localvocal
Canonical: https://ross.abutalabs.com/products/obs-localvocal
Homepage: https://obsproject.com/forum/resources/localvocal-live-stream-ai-assistant.1769/
Language: C++
License: GPL-2.0
License Family: copyleft
Topics: ai, obs, plugin, speech-to-text, whisper, live-streaming, livestream, obs-studio, obs-studio-plugin, openai-whisper, real-time-transcription, realtime-transcribe, realtime-translator, speech-recognition, transcription, translation, whisper-cpp
Last push: 2026-05-20T08:09:39+00:00

## Health v2 (maintenance only)
Score: 81/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 83, release rhythm 80, longevity 79
- inputs: {"age_days": 1119, "days_push": 105, "days_rel": 134, "gap_med": 8, "n_releases_24m": 18}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1585, forks 120 (observed 2026-08-28T04:05:07.354685+00:00)

## What it is
LocalVocal is an OBS Studio plugin that performs real-time, fully local speech recognition and translation using Whisper models running on the user's machine. It adds an audio filter that transcribes speech from any audio source and displays captions via text sources, files, or RTMP streams without cloud services.

## Use cases
- add live captions to my OBS stream without sending audio to the cloud
- transcribe microphone audio in real time during a livestream
- generate .srt subtitle files synced with my OBS recording
- translate my speech to another language live on stream
- send captions to YouTube or Twitch over RTMP
- run speech-to-text locally with no GPU and no network
- bring my own Whisper GGML model for transcription

## When to choose
- you stream or record with OBS Studio and need privacy-first, offline captions
- you want real-time transcription or translation with minimal lag and no cloud costs
- you need captions exported to text/SRT files or pushed to streaming platforms
- you want GPU acceleration via CUDA or AMD but can also run CPU-only

## When to avoid
- you need transcription outside of OBS Studio or for pre-recorded batch files
- you require a hosted or multi-user captioning service
- you use broadcasting software other than OBS Studio
- you need translation quality beyond what local Whisper/DeepL integrations provide

## Facets
- artifact type: plugin
- maturity: active
- function: speech-recognition, nlp, machine-learning
- domain: speech-processing, accessibility, media
- platform: windows
- tags: obs-studio-plugin, whisper-cpp, live-captions, real-time-transcription, translation, streaming, privacy-first, ggml, gpu-acceleration, localization, macos, linux, desktop

## Member repositories
- royshil/obs-localvocal (main) score 81

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:07.354685+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:55:38.259315+00:00, confidence not recorded.
  - readme: https://github.com/royshil/obs-localvocal (fetched 2026-08-28T04:05:07.354685+00:00, sha c5d49594a0a6)
  - homepage: https://obsproject.com/forum/resources/localvocal-live-stream-ai-assistant.1769/ (fetched 2026-08-29T11:26:14.311467+00:00, sha e3dcb19e4b2e)
- Data as of 2026-08-30T08:39:29.467469+00:00.