building realtime avatars @Anam__ai
London, England
Joined November 2024
- Tweets532
- Following113
- Followers848
- Likes783
Ben Carr retweeted
@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: go.anam.ai/c41/partner-livek…
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: go.anam.ai/dXLpQWy
Ben Carr retweeted
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.
🤝 Paid partnership
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: go.anam.ai/dXLpQWy
Ben Carr retweeted
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.
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: go.anam.ai/dXLpQWy
Ben Carr retweeted
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.
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: go.anam.ai/dXLpQWy
Ben Carr retweeted
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: anam.ai
🤝 Paid partnership
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: go.anam.ai/dXLpQWy
Ben Carr retweeted
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
🤝 Paid partnership
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: go.anam.ai/dXLpQWy
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: go.anam.ai/dXLpQWy
3 years of building @Anam__AI, and @Caoimhe_anam and we haven’t killed each other yet :)
Oct ‘23 we both quit our jobs to build the next interface for technology. The first few months were just the two of us trying to put together a deck, get a POC working, find our first customers and convince a few researchers and engineers to take a chance on us.
By May ‘24 we had money in the bank and our first 3 hires. Since then:
- #1 ranked real-time model, 3 releases in a row new models shipping every quarter
- 60K+ users signed up to try, buy and build on Anam
- XM+ monthly minutes in production over the last 4 weeks
- 14x ARR in the last 13 months
- a team of absolute superstars across GTM to research
- backed by some of the best VCs around
First pic is from hours of live testing our latest model in a dark room in the London office. Second is Caoimhe in my old apartment the night we got the very first POC working.
V cool to look back on, but we’re just getting started
On the back of Eleven v4 being released, we paired @elevenlabs v4 with Cara-4 on @Anam__AI and got an avatar performing a dramatic speech from Shakespeare’s Julius Caesar. Director notes handles the face (you cue anger, sadness etc as the speech turns) while v4 handles the voice, so they build together.
Then mid-session we switched it to Portuguese and then Hindi. Same voice ID, no restart, and it just picks up the accent each time. Pretty cool to see.
Director notes docs are here: anam.ai/docs/personas/direct…, and check out the video below.
A nice advantage of 1-shot avatars based off a single image--you can make edits real easy. Eg adding a logo takes ~1min
Personalize your @Anam__AI avatar's outfit and background 👕
Describe the look, attach your brand logo, and have it ready for conversations within 2 minutes.
A cool customer story - @getdocketai built an AI avatar, powered by @Anam__ai straight into their webpage, getting rid of chat widgets and forms. They've seen 41% increase in agent engagement since launch. Sounds a bit obvious but people love to speak to a face and its showing that.
Link to the full customer story is here: anam.ai/case-studies/docket-…, and check out their launch video below, its pretty good.
Ordering pizzas with Anam x GPT-Live
We gave GPT-Live a face! 🍕
OpenAI’s new voice model GPT-Live can listen while it talks. We built an integration with Anam so you can add an interactive avatar to the conversation.
To test it out, we built a pizza counter with a slightly sarcastic avatar taking your order.
Tell it which pizza you want, add your toppings, and see the order appear in a 3D preview. Change your mind halfway through? Just tell it. You can talk through the correction without clicking through a menu.
Under the hood, GPT-Live-1 handles the voice, Anam handles the real-time avatar, and LiveKit connects the two together.
If you’ve been building with GPT-Live-1, try giving it a face using Anam. Read the setup blog: anam.ai/blog/gpt-live-1-inte…
We’ve just added a cool feature that lets you personalize your @Anam__AI avatars. Upload a reference image and prompt the changes you want e.g. new background, jewelry, a branded outfit and then just keep prompting until its right.
Try it in the Anam Lab: lab.anam.ai/build
One of the weirdest things about talking to an AI agent is when it needs to look something up and just… freezes.
Humans don’t do that. We say “give me a sec” or “let me check.”
We just shipped this behaviour for @Anam__AI avatars.
Small detail, but it makes a surprisingly big difference.
We built a bunch of tools at @Anam__AI to show what you can actually do with real-time AI avatars.
Practice a language. Get grilled in an interview. Rehearse a sales call. Or just mess around in the avatar playground.
No account needed. Try it: anam.ai/tools?utm_source=x&u…
