Swiss startup unveils ‘world’s first’ AI translation service
A startup claims to have launched a world first in a speech-to-speech translation system with artificial intelligence.
The tool, called Aivia, was developed by interpreta Zurich-based translation service provider. The company focuses on meeting and event interpretation – a market that is being boosted by globalization.
As interactions spread across borders, they can become more difficult to understand. Although English is the language of international business, it is only spoken by an estimated group 17% of the world. The rest is often left out of the conversation.
Interprefy offers a way to overcome this language barrier — and the demand seems high. In the eight years since the company was founded, Interprefy says it has supported more than 50,000 meetings. They range from remote press conferences the European Championship 2020 football tournament interviews with astronauts on the International Space Station.
Visit us at TNW Conference 15 & 16 June in Amsterdam
Here are four reasons why you shouldn’t miss it
Aivia is designed to expand this customer base. At the touch of a button, the service translates speech into audio and subtitles in real time. interpret claims that it is the first-ever advanced automated speech translation service for online and live events.
“Many organizations and events lack the budget to book professional interpretation.
Oddmund Braaten, CEO of Interprefy, has big ambitions for Aivia. He wants the simultaneous translation tool to finally become mainstream.
“Over the past eight years, our remote interpreting technology has greatly democratized access to these services and gained widespread adoption, especially during the Covid era,” Braaten tells TNW.
“But we still saw that many organizations and events lacked the budget to book professional interpretation. That’s why we’ve developed a service that provides affordable real-time translation, as well as the flexibility and support needed to ensure a seamless multilingual user experience.”
Braaten is optimistic about the results. He believes Aiva is the most accurate and flexible AI speech translator on the market.
Under the hood, Aivia integrates three key AI technologies: automatic speech recognition, machine translation and synthetic speech generation.
To improve their output, Interprefy a benchmarking toolkit to evaluate the best AI for each language pair. The company also uses a glossary extractor tool to further customize Aivia for each event. This prepares the system with relevant keywords and hard-to-catch names or abbreviations of relevant content.
According to Brat, this approach addresses two shortcomings real-time speech translation: inconsistent results and the needs of event organizers.
“We think we’ve solved both pain points,” he says. “Having supported events of all shapes and sizes for nearly a decade, we have the expertise to provide hands-on support to event organizers. We also built a solution that can benchmark leading AI solutions to use only the best performing AI technologies available on the market.”
Initially, Aivia will be available in 24 languages and regional accents. Both personal audiences and platforms such as Microsoft Teams, Zoom and ON24 can use the service.
Interprefy plans to add many more languages in the near future – and rightly so. worldwide, estimated 30% of internet users now use online translation tools every week, but real-time speech interpretation remains a challenge. Aivia offers a new solution to the problem.
Aivia arrives amid rapid advances in AI translation. Last year, an Italian interpreting company already predicted that machines will surpass the best human translations by the end of the decade.
The progress naturally raises concerns about the profession’s future prospects. Braaten argues that AI and humans can play complementary roles.
Only skilled linguists, he says, can translate the subtleties of context, tone, humor and idiom. In addition, they are the only secure option for sensitive content.
“Interpreters have the unique ability to adapt their translation to any scenario, and can also paraphrase and interpret non-spoken information such as body language and intonation,” says Braaten.
“These are traits that AI simply cannot replicate and are especially important for higher-level communication, such as board meetings, legal meetings, or diplomatic conversations.”
AI, meanwhile, is better suited to situations where nuance is rare and risks are low. In these scenarios, machine translations can provide a more affordable and practical alternative.
But for live events and meetings, simultaneous interpretation remains a niche service. Braaten hopes that the accessibility of Aivia can change that.
