French AI research institute unveils 'Moshi,' an AI voice assistant capable of expressing emotions in real time
The French AI research institute
Kyutai unveils today the very first voice-enabled AI openly accessible to all
(PDF file) https://kyutai.org/cp_moshi.pdf
A video of Kyutai's presentation in Paris has been released, showing a demonstration of Moshi in action.
First, Moshi was introduced to the audience and responded, 'Hi, my name is Moshi. What can I do for you today?'
When asked about the creator, he smoothly explained about Kyotai, saying, 'It was developed by Kyotai, a non-profit AI research organization.'
When the other person takes over and says, 'I'm thinking of climbing a mountain,' the robot responds, 'That's wonderful,' while still trying to continue the conversation. There's almost no sense of waiting for the dialogue to be output, and it's clear that real-time responses are being achieved.
When the third interlocutor asked him to 'read a poem about Paris with a French accent,' he immediately began reading, 'Paris, the city of love, where time stands still and the heart takes flight.'
When asked to 'act like a pirate,' Moshi responded by becoming a pirate himself. 'What's your name? How's the pirate life? It's a wild ride, buddy? There's freedom, danger, and adventure at every turn,' he said, acting like a captain, and at times, the interlocutor had a hard time stopping him.
Anyone can experience the same content as this demonstration online.
moshi.chat
Kyutai developed Moshi from scratch over a six-month period with a team of eight people. It can be installed locally, so it can run safely even on devices without an internet connection.
Through Moshi, Kyutai is demonstrating its commitment to contributing to open AI research and the development of the entire ecosystem.
Related Posts:
in AI, Video, Web Service, Posted by logc_nt