Converts WhatsApp Web voice messages into readable text using an on-device transcription engine and optional AI APIs for tougher clips. Audio Transcriber – Voice Messages, built by Giulio Cinelli, integrates a Transcribe button directly into the WhatsApp Web interface and supports multi-language detection and word highlighting. It targets users who need to read voice notes in noisy offices, on shared devices, or when hearing is difficult, providing persistent text inside the browser for quick review and copying.

What the extension does inside WhatsApp Web

Audio Transcriber places a Transcribe button under each voice message and can automatically transcribe recent messages when a chat opens, letting you read audio content without leaving the browser. The extension exports transcriptions to a text file and offers one-click copying, so the workflow stays within WhatsApp Web rather than requiring separate tools or downloads.

How it handles languages and transcription sources

The extension provides a local engine that supports 25 European languages with automatic detection, and it also accepts external API keys from OpenAI, Groq, or AssemblyAI to broaden language coverage to about 100 languages. Users can choose the local engine for privacy or supply an API key when audio quality demands higher accuracy, which changes which engine processes the file.

Privacy model and data handling

The extension processes audio locally by default, so audio files do not leave the user’s computer unless the user opts to use a third-party API key. That design limits external data transfer, and persistent transcriptions remain visible after closing and reopening chats, keeping text available without reprocessing the same audio each time.

Playback sync and interface fit

Word highlighting syncs the displayed transcript to audio playback, which helps follow longer messages while reviewing text. The UI adapts to both light and dark browser themes and keeps a compact presence in the WhatsApp Web layout, preserving the look and ordering of chat elements rather than replacing them.

Clear fit for privacy-minded WhatsApp Web users who prefer reading

This extension suits people who need readable voice notes on the desktop and who prefer not to send audio to external servers, because it processes audio locally by default and keeps transcripts visible across sessions. Users who require broader language support or higher accuracy can connect external AI keys, but that choice shifts processing away from the local engine and alters the privacy model.