Live translation

Real-Time Translation API for Meetings and Webinars

MediaSFU translation workflows combine live media, transcripts, provider routing, language selection, and meeting or webinar context so multilingual communication stays inside the same RTC platform.

Open translation guideSee webinar use caseCompare pricingTry it live, no account →

The short answer

Each listener picks the language they hear. MediaSFU translates speakers in real time into spoken audio in a natural voice, with live captions, in meetings, events and calls, across 50+ languages.

Languages
50+, with an allowlist or blocklist per room and a chosen voice per language
Output
Translated speech plus live captions, with an optional transcript and AI notes
Who chooses
Every listener sets their own language; speakers talk naturally
Cost
The room bills at published rates (audio $0.0001 per minute); your speech and language providers bill you directly
Included minutes
Teams plans include translation minutes: about 100 a month on Pro and 1,000 on Scale
Free to start
50,000 free minutes that never expire, no card needed

Rates as published on the pricing page, checked 2026-10-26. Volume discounts apply automatically at scale.

01

What you can build

  • Translate live speech for meetings, webinars, training, support, and global events.
  • Capture transcripts alongside translated speech for review and accessibility.
  • Route STT, LLM, and TTS providers based on language and workflow needs.
02

Why MediaSFU fits

  • Translation connects to WebRTC rooms, recordings, AI notes, and live event paths.
  • Provider configuration and pipeline controls keep translation operationally visible.
  • Teams can pair translation with telephony fallback and webinar workflows.

MediaSFU translation capabilities

  • Speech-to-text, LLM translation, and text-to-speech pipeline configuration
  • Language selection, auto-detection, transcripts, and text-only translation paths
  • Meeting, webinar, training, support, and event translation workflows
  • Provider choice for STT, LLM, TTS, and custom translation pipelines
  • Recording, AI notes, and reusable multilingual session artifacts

Where to go next

This page is the short answer. These go deeper: implementation guides, pricing and the product pages behind it.

Questions people ask

Can MediaSFU translate live meetings?

Yes. MediaSFU supports live translation workflows that combine speech-to-text, language model translation, text-to-speech, transcripts, and provider configuration.

Can translation be text-only?

Yes. Translation workflows can include transcription and text-only output depending on the product experience and provider configuration.

Can translation work with webinars?

Yes. Translation can be paired with webinar, meeting, event, recording, and telephony-adjacent workflows.

Last updated: October 26, 2026