Skip to main content

Starting March 27, 2026, RC is rebranded as Nexconn. Existing RC SDK customers can continue using this documentation. New customers should refer to the Nexconn developer documentation.

AI Real-Time Speech Translation

AI Real-Time Speech Translation is an advanced feature built upon AI Real-Time Speech Recognition, offering low-latency, high-accuracy text translation across 200+ languages. For supported language codes, see: Speech Translation Language Codes.

Universal Use Cases​

  • Voice/Video Calls: Break language barriers in cross-border family chats or international business meetings with natural, real-time translation.
  • Multilingual Conferences: Boost decision-making efficiency in global team collaborations or academic seminars by delivering synchronized multilingual translations.
  • Cross-border Live Streaming: Expand audience reach for e-commerce livestreams or cultural content with instant translation, eliminating geographical and linguistic limits.

Prerequisites​

AI Real-Time Speech Translation is a premium feature of RC RTC SDK. To enable it, submit a ticket.

Note

This feature relies on AI Real-Time Speech Recognition. Client-side integration requires enabling speech recognition first.

Translation Settings​

Access subtitle settings via the speech recognition UI to configure Translation Display and Bilingual Subtitles.

tip

CallKit supports two subtitle modes:

  • Translation Only: Instantly grasp key information even with zero source language knowledge.
  • Source + Translation: Verify accuracy in professional scenarios (e.g., business meetings, academic discussions) if you understand the source language.
Last updated on