Google Meet translates in real-time while preserving the speaker’s voice

Post Thumbnail

Google has introduced a revolutionary real-time speech translation feature for its Meet video conferencing service. I am pleasantly shocked! The main feature of this technology is the ability to not only translate what is said, but also preserve the individual characteristics of the speaker’s voice. Including timbre, intonations, and emotional nuances.

The system works based on Gemini artificial intelligence and allows conversation participants to communicate across the language barrier, while maintaining the naturalness of communication. At the I/O conference, Google demonstrated this technology in action. In the demonstration, an English-speaking participant communicated with a colleague in Spanish. After activating the Gemini function, the system instantly began translating speech in both directions. And each participant heard the interlocutor in their native language while preserving the original voice characteristics.

Currently, the technology works only with English and Spanish languages, but the company has already announced plans to add support for Italian, German, and Portuguese languages in the coming weeks. Now the function is available to paid Google Meet subscribers, and by the end of the year, they plan to open it to corporate clients.

This technology potentially can change the approach to international communications, making them more natural and effective for business, education, and personal communication with foreign friends or relatives.

I am really surprised! Google Meet simultaneous translation focuses not only on the accuracy of meaning transmission, but also on preserving the paralinguistic elements of speech. Which makes communication between speakers of different languages as close as possible to natural communication. How cool it will be to talk to any person on the planet in any language. I’m really looking forward to this technology being widely available.

AIvengo > Reviews > Google Meet translates in real-time while preserving the speaker’s voice
Почитать из последнего
UBTech will send Walker S2 robots to serve on China's border for $37 million
Chinese company UBTech won a contract for $37 million. And will send humanoid robots Walker S2 to serve on China's border with Vietnam. South China Morning Post reports that the robots will interact with tourists and staff, perform logistics operations, inspect cargo and patrol the area. And characteristically — they can independently change their battery.
Anthropic accidentally revealed an internal document about Claude's "soul"
Anthropic accidentally revealed the "soul" of artificial intelligence to a user. And this is not a metaphor. This is a quite specific internal document.
Jensen Huang ordered Nvidia employees to use AI everywhere
Jensen Huang announced total mobilization under the banner of artificial intelligence inside Nvidia. And this is no longer a recommendation. This is a requirement.
AI chatbots generate content that exacerbates eating disorders
A joint study by Stanford University and the Center for Democracy and Technology showed a disturbing picture. Chatbots with artificial intelligence pose a serious risk to people with eating disorders. Scientists warn that neural networks hand out harmful advice about diets. They suggest ways to hide the disorder and generate "inspiring weight loss content" that worsens the problem.
OpenAGI released the Lux model that overtakes Google and OpenAI
Startup OpenAGI released the Lux model for computer control and claims this is a breakthrough. According to benchmarks, the model overtakes analogues from Google, OpenAI and Anthropic by a whole generation. Moreover, it works faster. About 1 second per step instead of 3 seconds for competitors. And 10 times cheaper in cost per processing 1 token.