Auto Captions for Video & Audio by Mehdi Abdi
Add automatic subtitles to web video and audio. Pick a language and get speech-to-text captions generated on your device.
Available on Firefox for Android™Available on Firefox for Android™
46 Users46 Users
Scan the QR code to open this extension in Firefox for Android
Extension Metadata
Screenshots
About this extension
Add automatic subtitles to video and audio on the web.
This extension adds a small CC button to HTML5 video and audio players. Choose a language, play your media, and the extension generates captions from speech—even when the media has no subtitles or transcript of its own.
Speech recognition runs locally in your browser using the open-source Vosk engine through the voice2text library. Your media audio is not uploaded to a server. The extension downloads speech-recognition model files when needed; it does not send your audio or generated captions to a server.
English, Spanish, French, German, Italian, Portuguese, Dutch, Russian, Ukrainian, Polish, Czech, Turkish, Arabic, Persian, Hindi, Chinese, Japanese, Korean, Vietnamese, Catalan, Kazakh, Uzbek, Breton, Esperanto, Greek, Swedish, Gujarati, Tajik, Telugu, Kyrgyz, Georgian, and Tagalog.
This extension uses Vosk (Apache 2.0) and voice2text (MIT).
For privacy details, please see the linked Privacy Policy.
This extension adds a small CC button to HTML5 video and audio players. Choose a language, play your media, and the extension generates captions from speech—even when the media has no subtitles or transcript of its own.
- Open a page with a video or audio player and hover over it. Audio players show the button when available.
- Click the CC button next to the player.
- Choose your language. The first time you use a language, its speech-recognition model is downloaded. Model files can be tens of megabytes and may take a moment to download. They are then stored in your browser for reuse.
- Play the media. Captions appear as the audio is processed and follow playback, including when you pause or seek.
Speech recognition runs locally in your browser using the open-source Vosk engine through the voice2text library. Your media audio is not uploaded to a server. The extension downloads speech-recognition model files when needed; it does not send your audio or generated captions to a server.
English, Spanish, French, German, Italian, Portuguese, Dutch, Russian, Ukrainian, Polish, Czech, Turkish, Arabic, Persian, Hindi, Chinese, Japanese, Korean, Vietnamese, Catalan, Kazakh, Uzbek, Breton, Esperanto, Greek, Swedish, Gujarati, Tajik, Telugu, Kyrgyz, Georgian, and Tagalog.
- Caption accuracy depends on the audio and language model. Background noise, music, and overlapping speakers can reduce accuracy.
- Some websites use cross-origin media or protected streaming that prevents the extension from accessing audio. In those cases, captions may not be available.
- Captions are generated as the media plays, so they appear shortly after the words are spoken.
- For audio players, captions appear below visible players. For hidden audio elements, a floating control may appear after playback has been running for a few seconds.
This extension uses Vosk (Apache 2.0) and voice2text (MIT).
For privacy details, please see the linked Privacy Policy.
Rated 5 by 1 reviewer
Permissions and data
Required permissions:
- Access your data for all websites
Optional permissions:
- Access your data for voice2text-proxy.mehdiabdi.com
Data collection:
- The developer says this extension doesn't require data collection.
More information
- Add-on Links
- Version
- 1.0.0
- Size
- 3.3 MB
- Last updated
- a month ago (Oct 13, 2026)
- Related Categories
- License
- All Rights Reserved
- Version History
- Add to collection