Vozelle: Voice Translator, Video & Audio Dubbing, developed by Carlos Brito, converts browser audio into translated speech for listeners who prefer audio over text. The extension captures tab audio, auto-detects the original language, and outputs spoken translation in near real time across videos, podcasts, and online calls, with a zero-setup, three-click workflow. Core features include support for 77 languages, encrypted audio streaming, and adjustable output that plays about three seconds after the original. It targets language learners, international professionals, and global media consumers who prefer listening.

Vozelle concentrates on spoken translation instead of text captions

The extension captures audio from any Chrome tab and produces spoken translations, making it suited to users who want to listen rather than read. It supports 77 languages and performs automatic source-language detection, so setup reduces to selecting a target language and activating translation. Typical uses include translated playback of videos and podcasts, and hearing translated speech during web calls; the translated voice plays back inside the same browser tab.

Playback timing favors media consumption over rapid exchanges

Translated output typically begins roughly three seconds after the source audio, creating a short audible lag that affects conversational rhythm. Because translation runs inside Chrome, the flow fits one-way listening and asynchronous content consumption more than tight back-and-forth dialogue. Users planning to use the extension in live meetings should test it on brief sessions to assess how the delay interacts with their meeting style.

Audio handling is designed around transient, encrypted processing

Audio is streamed to the translation pipeline in encrypted form, and the developer states that audio is translated in real time and immediately discarded rather than stored. Encrypted audio streaming and the stated absence of retained recordings reduce persistent server-side copies of audio. The automatic detection and live processing keep data transient during each translation session.

Voice-first design suits listeners but limits caption-dependent workflows

Choosing this extension fits commuters, podcast listeners, and multitaskers who prefer auditory comprehension. The design intentionally emphasizes spoken output over written captions, so users who require searchable transcripts, captions, or text-based review may find a subtitle fallback necessary. Pairing the extension with separate caption or transcription tools addresses those needs while preserving the listening-focused workflow.

A practical choice for listeners who want translated audio, with a clear trade-off

Vozelle is a practical option for users who prefer hearing translated speech inside Chrome rather than relying on captions; it integrates directly with browser-based media and web meetings. As a trade-off, users who need searchable text or very tight conversational timing should test the extension in low-stakes sessions first. Tip: use headphones to keep the translated voice distinct from original playback during testing.