AI BriefingElevenLabs launches Eleven Realtime Translation for live multilingual voice calls
·2026.10.21 21:00
Key point
The new model uses Eleven v4 Turbo to provide low-latency, expressive voice translation for enterprise customers in alpha.
Details
- ElevenLabs has launched Eleven Realtime Translation, a live voice translation model available in alpha for ElevenAPI enterprise customers.
- The system uses Eleven v4 Turbo, a low-latency speech model, to support more than 90 languages with automatic language detection and consistent voice performance.
- Users can select from a library of over 17,500 voices or use Instant and Professional Voice Clones, with the chosen voice remaining consistent throughout the session.
- Deployment settings allow teams to tune the balance between translation quality and latency, suitable for use cases ranging from complex billing calls to fast back-and-forth conversations.
- Deutsche Telekom is integrating the technology into its Magenta AI Call Assistant to enable new multilingual calling features.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
OpenAI Releases GPT-Live-1.1 with New Voices and Improved Accents for ChatGPT, Codex, and Dots