Languages

Category: Utilities
Status: stable

A browser-based connector for live speech recognition, automatic translation, and text-to-speech playback. No server-side components required — all processing runs in the browser using built-in Web APIs and a free translation service.

---

Features

Speech-to-Text

Converts spoken audio into text in real time using the browser's built-in Web Speech API.

• Continuous recording — keeps listening until you stop
• Interim results — shows text as you speak (greyed out), finalised on pause
• Language-aware — recognition language follows the From selector
• Works in Chrome and Chromium-based browsers (Edge, Opera). Not available in Firefox or Safari.

Automatic Translation

Translates recognised (or manually entered) text into the target language.

• Translation triggers automatically 600 ms after the last speech input
• Powered by an external translation service (configurable)
• Supports 15 languages (see list below)
• Same-language pair → text is copied as-is without a network call

Text-to-Speech

Reads the translated text aloud using the browser's SpeechSynthesis API.

• Voice language matches the To selector automatically
• Long texts are split into sentence-sized chunks to avoid Chrome's ~15-second voice cut-off
• Supports pause / resume during playback

---

Supported Languages

Code	Language
en	English
ru	Russian
de	German
fr	French
es	Spanish
it	Italian
pl	Polish
pt	Portuguese
zh	Chinese
ja	Japanese
ar	Arabic
ko	Korean
nl	Dutch
tr	Turkish
uk	Ukrainian

---

Interface

Control	Description
From selector	Source language for speech recognition and translation input
To selector	Target language for translation and text-to-speech
⇄ Swap button	Swaps source and target languages, retranslates current text
🎤 Mic button	Start / stop recording. Orange = recording in progress
🗑 Clear button	Clears recognised text and translation
Original pane	Shows interim (grey italic) and final recognised text
Translation pane	Shows translated text
🔊 Speaker button	Reads translated text aloud. Click again to pause / resume
Copy button	Copies translated text to clipboard

---

Browser Requirements

Feature	Requirement
Speech recognition	Chrome 33+, Edge 79+, Opera 36+
Translation	Any browser (outbound HTTP request)
Text-to-speech	All modern browsers

If speech recognition is not available, an error message is shown in the panel and the mic button is disabled.

---

Connection Settings

No credentials required. The connector does not connect to a database.
Translation calls are made directly from the browser to the translation service endpoint.