For businesses running large customer operations, language is one of the hardest constraints to scale. A customer calling in one language often waits on hold for an agent who can understand them, and often has to deal with questions in a language they don’t speak as fluently.
Today we're launching Eleven Realtime Translation, our live voice translation model, available in alpha for ElevenAPI enterprise customers.
With Eleven Realtime Translation, each person speaks in their own language and hears the other in theirs, in a natural, expressive voice, while the conversation is happening. Telecom operators can build it into the calling layer, so calls on their network work across languages. Contact centers can place it between agent and caller, so one agent can help customers in many more languages without bringing an interpreter onto the call. At live events, each attendee can hear the speaker in their own language.
Deutsche Telekom is already building new calling features with ElevenLabs as part of its Magenta AI Call Assistant.
One voice across more than 90 languages with Eleven v4 Turbo
Eleven Realtime Translation uses Eleven v4 Turbo, our low-latency speech model optimized for realtime applications by default. A single voice performs more consistently across multiple languages, so a brand or an agent sounds consistent in every market, available in more than 90 languages with automatic language detection.
Choose your voice
You choose the voice. Choose any voice from more than 17,500 voices in our library, or build your own Instant or Professional Voice Clone. That voice will stay consistent for the entire session.
Built for your use case
Every deployment can be tuned to the conversation. Teams set how quickly translation starts, from higher-quality translation for complex calls like billing or claims, to the lowest latency for faster back and forth.
Available in alpha in ElevenAPI
Eleven Realtime Translation is available in alpha for enterprise customers in ElevenAPI.