A research prototype exploring future capabilities of a universal AI assistant
Project Astra is on your phone and prototype glasses, helping you explore your world like never before.
You can speak to Project Astra or use video to show what you see.
Real-time conversations
Fast responses and free-flowing conversation create a seamless experience.
Memory
Project Astra refines its answers by remembering key details of past conversations - as well as up to 10 minutes of its current session.
Tool use
Ask a question and Project Astra can use Google Search, Maps and Lens to inform its answers.
A group of trusted testers are exploring Project Astra’s capabilities, and uncovering new uses for a universal AI assistant.
Our testers' feedback is helping us refine and improve the experience.
You can use Project Astra on Android phones or prototype glasses. Memory allows you to keep talking even if you swap device.
Mobile
Point your phone camera at what you’re interested in, and start a conversation. Or share your screen to unlock a new level of interactive assistance.
Glasses
Project Astra integrates seamlessly with prototype glasses to see the world as you see it – for an even more immersive and helpful experience.
As we develop these new technologies, we recognize the responsibility it entails, and aim to prioritize safety and security in all our efforts.
Project Astra is a research prototype, being used and refined by a limited number of trusted testers. If you're interested in becoming a tester, please share a few details to join the waitlist.
Acknowledgements
This work was made possible by the exceptional contributions of: Aaron Donsbach, Aaron Schneider, Agustin Dal Lago, Alejandra Molina, Alexandre Moufarek, Alistair Muldal, Allison Garcia, Anand Rao, Andrea Colaco, Anirudh Baddepudi, Arun Ahuja, Arun Narayanan, Bethanie Brownfield, Bhanu Guda, Bibo Xu, Bob Muniz, Chen Yan, Cindy Fan, CJ Zheng, Daniel Padgett, Darren Carikas, David Wood, Diane Wan, Duncan Williams, Elisabeth Chauncey, Ewa Dominowska, Federico Carnevale, Fei Zheng, Gan Song, Golan Pundak, Grant Yoshida, Gregory Wayne, Haokai Lu, Haoting Wang, Haozhen Wu, Jeff Gray, Jens Heitkaemper, Jiaxi Tang, Jesper Andersen, John Penington, Jonas Degrave, Jordan Griffith, Julie Anne Seguin, Julie Sohn, Khe Chai Sim, Kitty Stacpoole, Lin Li, Liviu Panait, Lucia Rossazza, Mark Lieu, Mehdi Mirza, Michael Chang, Michal Lahav, Mike Dory, Misha Dashevskiy, Nikolai Grigorev,Oscar Chang, Patrik Sundberg, Paul Pucciarelli, Pavel Dubov, Pengfei Xing, Praveen Srinivasan, Pu-Chin Chen, Reed Roberts, RJ Skerry-Ryan, Rob Willoughby, Sadh MNM Khan, Sage Stevens, Sam Castle, Sean Csukas, Seth Welna, Shaan Bijwadia, Shefali Garg, Shenil Dodhia, Shuo-yiin Chang, Stephanie Zhang, Steven M. Hernandez, Suz Chambers, Tanuj Bhatia, Tara Sainath, Tanya Kraljic, Taylor Bos, Tim McConnell, Timothee Cour, Tony (Tuấn) Nguyễn, Tom Ouyang, Tony Bruguier, Toshiyuki Fukuzawa, Václav Novák, Vahid Ghadakchi, Vikas Bahirwani, Virat Shejwalkar, Vivek Kesarwani, Wing Wat, Xi Yi, Xiaotong Yang, Xingyu Cai,Yana Lunts, Yanzhang (Ryan) He, Yao Fu, Yaqing Wang, Zack Ontiveros, Zhouyuan Huo, Zilla Gunawardana.
We extend our gratitude to Adrian Bolton, Alex David Norton, Alex Chen, Alex Greve, Alex Grills, Andrea Colaco, Andrew Rhee, Angad Chandorkar, Ankesh Anand, Anurag Ajay, Bakary Diarrassouba, Bo Li, Chandu Thota, Christopher Yew, Clement Farabet Dana Kurniawan, Dan Motzenbecker, Dawn Bloxwich, Demetra Brady, Dimple Vijaykumar, Elahe Dabir, Emanuel Taropa, Evan Palmer, Evan Senter, Fred Alcober, Gaby Pearl, Georgi Stephanov, Hadas Natalie Vogel, Jack Huo, Johnny Lee, Joe Stanton, Jon Blanton, Jonathan Fildes, Julian Salazar, Julie Anne Seguin, Juliette Love, Junwen Bai, Juston Payne, Keerthana Kumar, Keran Rong, Komal Jalan, LeHan Meng, Liangliang Cao, Liangzhe Yuan, Lichan Hong, Lihao Liang, Maciej Kula, Maxine Deines, Michael Severino, Michael Siliski, Mikel Rodriguez, Mingqiu Wang, Naina Raisinghani, Nathaniel Fruchter, Nishtha Bhatia, Oskar Bunyan, Pankil Botadra, Piermaria Mendolicchio, Prakash Shroff, Pramod Gupta, Ronny Huang, Ross West, Sami Lachgar, Sam Lawton, Scott Adams, Stav Ginzburg, Terry Tai, Vijay Bolina, Wei Huang, Woohyun Han, Zeina Oweis.
We also acknowledge the many other individuals who contributed across Google DeepMind and our partners at Google.
Fast responses and free-flowing conversation create a seamless experience.
Audio and video
Engages and responds to live speech, images and video.
Low latency
Responds to requests at a conversational pace, for a seamless experience.
Multilingual
Hold conversations and translate input into the language of your choice.
