Fast path: managed translation is available

Use MediaSFU-managed configs from LiteDashboard Settings. Bring your own STT, LLM, and TTS providers only when you need direct provider, model, or billing control.

Overview

Multilingual rooms

Run real-time translation, transcripts, translated audio, and AI notes from one room setup.

TranslationConfig connects STT, LLM, and TTS into a live pipeline. Use managed configs when you want the fastest start, or bring your own providers when you need direct control.

Prove it in 30 secondsHear live translation before you configure a pipeline.
50+languages in real timeIncluded in team plans — Pro adds ~100 translation minutes monthly

Speech Recognition

Convert spoken audio to text with high accuracy using leading STT providers

AI Translation

Leverage powerful LLMs to translate text while preserving context and nuance

Voice Synthesis

Generate natural-sounding speech in the target language with customizable voices

50+ Languages

Support for major world languages with extensible language configuration

Meetings

Live multilingual participation

Let participants speak and listen in the languages that match the room, meeting, webinar, or training session.

Transcripts

Capture text alongside speech

Use transcription to support accessibility, search, notes, and post-session review.

AI notes

Summaries without forced audio playback

Enable AI Notes or notes-only mode when the goal is transcript and summary artifacts rather than translated voice.

Control

Use managed or BYOK providers

Start with managed configs when eligible, or bring your own STT, LLM, and TTS credentials for provider-level control.

Prerequisites:

Quick Start

Architecture

Configuration

Supported Languages

Provider Types

Pipeline Configuration

Voice Overrides

API Examples

Room Integration

Best Practices

Troubleshooting