Dan Bigioi

Research @tavus , studied Neural Talking Head Generation / Automatic Dubbing / Facial Animation as part of my PhD @nuigalway

[Hassaan Raza @hassaanraza]

Last week Apple previewed the future of Siri. In 1987 though, Apple showcased a far more advanced AI assistant that would change how we use our computers entirely. It could see you, control your computer, and even looked and sounded human. They called it Knowledge Navigator.

For nearly 40 years it remained science fiction. This past week at @tavus we finally brought it to life with the help from our friends at @cerebras.

Meet Dom:

[Mirage @trymirage]

Curious how it works? Our research team shared a peek into their discovery process on our blog.

https://t.co/qXhEYEF1im

[#CVPR2026 @CVPR]

Check out our sponsor @getcaptionsapp. Reach out to the @getcaptionsapp team at #CVPR2025 to learn more about Mirage or chat expressive multimodal generation 🎥

[Drew Jaegle @drew_jaegle]

The Mirage technical report and website is now live!

At @getcaptionsapp we're big believers in simple recipes + an amazing focused team + fast iteration + getting the right things right, in our research and product

Check out the website & paper 👇 for tons of examples of all the emotions, expressions, and settings Mirage can generate

[ShahRukh Athar @shahrukh_athar]

The tech report of Mirage is out! Some nice details of how we got everything working 🙂

[Dan Bigioi @DBigioi]

@elonmusk @PJaccetturo Hells yeah, future is now

[Elon Musk @elonmusk]

@PJaccetturo AI shows will be incredible

[Mirage @trymirage]

Make a music video without ever leaving your house. H/t @SunoMusic for the track.

[Mike Vernal @mvernal]

E.g., a music video for a @SunoMusic track.

[Mirage @trymirage]

Introducing Mirage Studio.

Powered by our proprietary omni-modal foundation model.

Generate expressive videos at scale, with actors that actually look and feel alive. Our actors laugh, flinch, sing, rap — all of course, per your direction.

Just upload an audio, describe the scene or drop in a reference image, and create energetic content in minutes.

Built for marketers, creative teams, and anyone serious about crafting great narrative videos.

Available for everyone at mirage dot app.

Get started with a few ideas below.

[Midas Kwant @Midaskwant]

Pretttyyyy special if you ask me

[Mirage @trymirage]

Mirage, day 2.

AI lip-sync model vs. Mirage.

Note: the person on the right is not real.

[el.cine @EHuanglu]

AI-lip syncing is officially done

Captions' new AI model, Mirage, can analyze a script or audio clip and instantly generate a UGC-style video of people that don't exist.

the facial expressions and body language are much more 'real' than the old ways

let's dive in:

[Mirage @trymirage]

Mirage is LIVE

Generate energetic, high-converting ads with people that don’t exist — complete with animated body language and micro-expressions — using Mirage, the first foundation model built to generate UGC-style content.

Get started with a script or an audio file, then specify the look of your spokesperson, their background, outfit, objects, and even emotion.

It’s never been easier to iterate and scale ad production with Mirage, now available in Captions Ad Studio.

[el.cine @EHuanglu]

this new audio-to-video AI is incredible..

Captions AI now can generate people from audio clips and.. their expressions and body movements match the tone perfectly.

this is the first in AI world

8 examples:

[Robin Delta @heyrobinai]

AI just changed the game again.

Captions dropped an early look of the first audio-to-visual foundation model, and these are the most realistic talking videos I've seen yet.

Here are 8 mind-blowing examples:

[Dan Bigioi @DBigioi]

An early look into what our team has been working on at @getcaptionsapp ! It has been super exciting working on Mirage and we’re all looking forward to the full release!

[Drew Jaegle @drew_jaegle]

An early look at our audio-to-video foundation model, Mirage. Made by the team at @getcaptionsapp.

Mirage generates expressive humans that don't exist — talking, laughing, yelling, and more

The videos below were created directly from audio input, without reference images

[Dan Bigioi @DBigioi]

Had a really great time at the Symposium on Computer Animation at Durham Uni this week! Got to attend some really cool presentations, and meet some even cooler people! Can’t wait till the next one :) #SCA2022

[Dan Bigioi @DBigioi]

@bradtravelers I see, thank you for the info!

[Dan Bigioi @DBigioi]

@DREAL_ie Thank you!