royshil/obs-localvocal

Health v2 · maintenance only

Adoption not part of the score

1585 stars · 120 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

plugin · maturity active

speech-recognition nlp machine-learning speech-processing accessibility media windows obs-studio-plugin whisper-cpp live-captions real-time-transcription translation streaming privacy-first ggml gpu-acceleration localization macos linux desktop

Member repositories

For agents

markdown · JSON · MCP: product_card(name="royshil/obs-localvocal")