We’re a research-led product company

Cara-4 built on Cara-3’s improvements to lip sync, eye movement and head motion. Cara-4.1 Express continues that work with expressive real-time avatars and control over how an avatar performs a conversation. A feature we call Director Notes.

A face that keeps up with the conversation

The right performance depends on the job. A distressed patient should not behave like a self-assured sales coach. An angry customer needs a different presence from a supportive therapist or a warm language tutor.

Director Notes, introduced in beta with Cara-4, lets you set that direction. Choose a preset style such as warm, supportive, angry or distressed, or write a short custom prompt such as:

Keep steady eye contact. Stay composed and attentive. Use restrained movement, as if coaching someone through a difficult conversation.

The Expressivity control then determines how strongly Cara-4.1 Express follows that direction. Turn it down for a steady, understated performance or up when the situation calls for more energy.

But real conversations do not stay in one emotional register, so we’ve made Director Notes dynamic. During a session, the LLM can add performance cues as it streams the spoken response, shifting the avatar from curious to concerned to warm within a single turn.

We still have a long way to go: prompt adherence is not yet where we want it, and Cara-4.1 Express cannot deliver the full range of gestures and actions a developer might want to direct, such as typing on a keyboard while looking something up. But this is the first step towards giving builders full control over how their avatar performs.

Built for the screens people use

Cara-4.1 Express renders natively in both landscape and portrait: 1152×768 or 768×1152. That’s ~2.5 times the pixels of Cara-3, but the more important change is portrait being a first-class output.

On a phone, we no longer need to render a landscape frame and discard the sides. The model spends its pixel budget on the part of the screen the user can see. Our longer-term goal is arbitrary output sizes within a compute budget, so builders can optimise the experience for a phone, an iPad or a layout we haven’t anticipated.

More ways to look like yourself

Custom avatars no longer need to come from a conventional photo. Cara-4.1 Express can animate a wider range of images, including animated 3D characters or anime.

This matters for products with a visual world of their own. The face of an agent can now feel native to a learning app or consumer brand rather than looking pasted in from somewhere else.

Built for production

In production, quality is only part of the job. An avatar also needs to start quickly, respond consistently and remain economical at meaningful volume.

In our full-pipeline benchmark (see Avatar Benchmark, October 2026), Cara-4.1 Express measured 1.24 s median reply latency and 1.42 s median connection time. Reply latency runs from the end of your sentence to the start of the avatar’s reply; connection time runs from pressing Start to the first visible avatar frame. Enterprise customers can also choose zero data retention and regional data residency options.

Cara-4.1 Express comes with improvements to model architecture, inference performance and hardware utilisation which have reduces the GPU cost of high-volume deployment. We are passing these savings onto customers, opening up new avatar use-cases previously difficult to justify.

What comes next

We have already started work towards Cara-5: more expressive, more controllable, higher fidelity and lower latency.

Our aim is for Anam to continue being the clear choice for real-time avatars without asking builders to trade quality against speed, flexibility or price.

Cara-4.1 Express is available now in Anam Lab and through the API with avatarModel: "cara-4-1-express". You can also invite your avatar to a Zoom, Microsoft Teams or Google Meet call with a click. Read the model guide, explore Director Notes, or start building in Anam Lab.