Ben Carr

building realtime avatars @Anam__ai

[Ben Carr @benatanam]

Proud celts over here 🏴󠁧󠁢󠁳󠁣󠁴󠁿 🇮🇪

[Caoimhe @caoimhe_anam]

We also get asked ALL the time what @Anam__AI means + why we called our model Cara, so we share a little on that too @benatanam

Try it here: https://t.co/bEro698jt4

[Caoimhe @caoimhe_anam]

We shipped Cara-4.1 Express this week: better lip sync, more expressive + way faster to connect.
#1 model across 6 metrics vs the market in blind human evals.
Why does it matter?? More natural convos = longer chats = better outcomes for our customers.

[Ben Carr @benatanam]

@Anam__ai Anam’s visual-quality lead over Tavus was not statistically significant. Evaluation code and methodology are public, so you can reproduce the results.

Results: https://t.co/Q6CLd9CwJw

Repo: https://t.co/Tm2Y70bXPU

[Ben Carr @benatanam]

Full results from our Cara-4.1 Express evaluations.

60 people held 960 blind conversations with avatars from @Anam__AI, Tavus, HeyGen and LemonSlice, rating each on six questions.

[Ben Carr @benatanam]

@Anam__ai Across all six questions, 73% of Anam ratings were positive vs 54% for Tavus. 53/60 raters scored Anam higher than Tavus; 51/60 than HeyGen.

Median reply time: 1.24s vs HeyGen’s 1.82s.

Median connection time: 1.42s vs HeyGen’s 3.66s.

[Ben Carr @benatanam]

@stronghamjji @Anam__ai Yes all English but will do other languages in the future, is there a certain language you'd like to see included?

[Ben Carr @benatanam]

Cara-4.1 Express is now live at @Anam__AI

Faster and more expressive than cara-4 with better lip sync and stronger prompt adherence. It also handles much wider framings for custom avatars.

We ran blind human evals: 85% of raters scored Anam higher than HeyGen, 88% higher than Tavus and 92% higher than LemonSlice. The eval code is public and reproducible.

Try it in the Anam Lab: https://t.co/0TXpYwwjA2

[LiveKit @livekit]

@Anam_AI ran its new blind benchmark on a LiveKit pipeline, with the same speech recognition, LLM and voice for every provider, so the only thing that changed was the avatar.

If you're building a voice agent with LiveKit Agents, you can give it a face in a few lines of code.

Try it now: https://t.co/tlTCa5QvOD

[Ben Carr @benatanam]

@livekit @anam_ai We're so happy to be livekit partners and provide our avatar models through livekit 🙌

[Rishabh @Rixhabh__]

AI avatars have looked realistic for a while.

The problem starts when you actually talk to them.

Anam's new Cara-4.1 Express responds in just 1.2 secs, handles interruptions, and makes eye contact feel natural.

This is getting surprisingly close to a real conversation.

[Rony @Ronycoder]

AI avatars can look impressive in a demo.

Then you start talking to them, and the awkward pauses, expressions, or lip sync give them away.

That's what makes Cara-4.1 Express from @Anam__ai so interesting.

1.2s response time, better lip sync, and more natural reactions are aimed at making conversations feel less robotic.

The real test isn't how an avatar looks in a still frame.

It's how it feels in a conversation.

[céline ✧ @celineodier]

YOU COULD GET 25%+ MORE CONVERSIONS FROM YOUR AI SALES AGENT JUST BY GIVING IT A FACE.

Cara-4.1 express from @Anam__AI is a real-time face builders can add to their agent:

→ 70% prefer it to voice-only
→ 57% higher retention
→ real-time conversations in 70+ languages

this could literally lift conversion across every funnel. we're definitely testing it in ours.

[Pratham @Prathkum]

Every AI avatar looks great for about 5 seconds.

Then you actually talk to it. dead eyes, lips a little off, that weird pause before every reply. the whole thing falls apart.

Anam just released Cara-4.1 Express and it’s the first one that looks like it’s trying to fix that part.

Conversational AI went text, then voice, now video. We trust a face more than a text box, and adding one to a text or voice agent drives a 44% increase in engagement.

What stands out to me:

– 1.2 seconds response time, 33% faster than the next best competitor
– you can interrupt it mid-sentence and it handles it like a real conversation
– 73% of ratings positive vs 54% for Tavus
– #1 overall in a blind benchmark with 60 raters and 960 conversations

Free to start: https://t.co/tEygAd5fOZ

[Ben Carr @benatanam]

@viannaopju @dravenip Agreed, but I'm confident it wont be feel like bad wifi. Try it, would love your feedback!

[Ben Carr @benatanam]

@piariapc @dravenip Test it - its free to start :) And let us know what you think

[Ben Carr @benatanam]

@Rixhabh__ It is...we have another model launching in a few weeks too - keep an eye out, you'll love it

[Parul Gautam @Parul_Gautam7]

the thing that makes an AI avatar feel real isn't just how it looks, it's how naturally it responds

Anam’s new Cara-4.1 Express model has better expressions, smoother lip sync, and came out #1 again in another blind test against its competitors.

I'm curious to see how developers use this for AI tutors and interactive assistants. it’s human nature, students pay more attention to a face

#AnamPartner

[Ben Carr @benatanam]

@aaliya_va @Parul_Gautam7 Agreed. People read faces before they hear words

[Ben Carr @benatanam]

@ajaysharma_here @Parul_Gautam7 100%. Tutoring is one of our biggest use cases, and expressions are a big part of why it works

[Ben Carr @benatanam]

@Div_pradeep @Parul_Gautam7 Exactly, and the details are where most of the work goes. Glad it shows

[Ben Carr @benatanam]

@aaliya_va @Anam__ai Thank you, try it out - we'd love your feedback