LocalVocal: Local Speech-to-Text Plugin for OBS
Easily transcribe audio with LocalVocal, a plugin for OBS that runs locally, ensuring privacy and offering customizable options for subtitle output.
File
Live Caption Translation with LocalVocal AI on OBS [Tutorial]
Added on 01/29/2025
Speakers
add Add new speaker

Speaker 1: Welcome to LocalVocal, an OBS plugin for speech-to-text transcription that runs locally on your machine. This plugin is enabled right now and the captions that you are seeing at the bottom of the screen are generated by this plugin. What makes this plugin special is that it does not send any of your information to any cloud providers that you have to pay for. All of the computation happens locally on your machine. To get started with LocalVocal, it's very simple. Just go on the plugin page in the OBS Studio plugins directory and go to Downloads. This will bring you to GitHub where you can get the very latest version of LocalVocal. We have several installers for different operating systems like Mac, Windows, and Linux. Click the one that corresponds with your machine and install that. If you get any messages for antivirus or malware, please ignore them. This plugin is completely safe. Once you have installed the plugin, you will see it in OBS for any audio outputting source, like this one for example. You will see an option to add LocalVocal transcription filter through the Audio Filters menu. Once you add it, you have a few options for debugging, like seeing things in the logs and so on, as well as choosing an output for your subtitles. Right now, you can either have no output and only see it in the logs, or you can send it to a text file, which can be picked up by other sources, or send it directly to a text source that you have in this scene or another scene. Another option here would be to change the model. The tiny models are small and efficient and good for low resources of CPU. The English model works only in English. The other ones would work for about 100 languages. The performance of those models could vary. Once everything is set up in here, there are more parameters for you to choose from, like the number of threads, or different settings for the Whisper AI speech-to-text model that you can play with and see if it makes for your transcription to be better. Once you choose an output, you should start seeing that in OBS as part of that text output. Your text outputs provide for a lot of styling and appearance options, so you can use them to set up your captions to appear on screen in the place and the shape that you'd like. In the future, we will be adding features to output the captions also to a streaming source like RTMP. I hope that you find this plugin useful for you. Please like and subscribe, and I will see you in the next video.

ai AI Insights
Summary

Generate a brief summary highlighting the main points of the transcript.

Generate
Title

Generate a concise and relevant title for the transcript based on the main themes and content discussed.

Generate
Keywords

Identify and highlight the key words or phrases most relevant to the content of the transcript.

Generate
Enter your query
Sentiments

Analyze the emotional tone of the transcript to determine whether the sentiment is positive, negative, or neutral.

Generate
Quizzes

Create interactive quizzes based on the content of the transcript to test comprehension or engage users.

Generate
{{ secondsToHumanTime(time) }}
Back
Forward
{{ Math.round(speed * 100) / 100 }}x
{{ secondsToHumanTime(duration) }}
close
New speaker
Add speaker
close
Edit speaker
Save changes
close
Share Transcript