Agent config

Customise how your AI sales agent looks and behaves.

Your install snippet

Paste this on your website. The data-tenant key links every chat, lead, and document to your account only.

Loading…

Agent name

Displayed in the chat header and greeting messages.

Photo

A square image shown as the agent avatar in the chat, until the live video avatar connects. PNG, JPG, GIF or WebP, up to 5 MB.

None

Or use one of ours

Picking a face fills in the name too — you can change it straight after.

Email me a daily summary Sent each morning: visitors, new vs returning, top pages, where your traffic came from, chats and leads captured — for the site where you installed the widget. Send to — comma-separated. Leave empty to use your account's admins.

Preview yesterday's report — opens the real email without sending it.

Ask for name and email before chatting Visitors see a short form instead of the message box, and the agent won't answer until it's filled in. Everyone who does appears in Contacts with their details. Off by default: it turns anonymous browsers into named leads, but the ones who won't give a name simply don't chat.

Require a phone number too The phone field is always shown. Tick this to make it mandatory — it is the field people abandon a form over, so expect fewer chats. What the form says — leave empty for the default.

Show the avatar Off by default. The agent still speaks every reply aloud over the photo — only the moving face is hidden. Leave this off unless the GPU is running: it bills by the second, and none of the avatar backends below will connect while this is unchecked.

Live photoreal avatar (optional, needs a GPU)

The real thing: a GPU box lip-syncs real footage of the person to every sentence she actually says. Everything in the stack is free and self-hosted — the GPU is the only cost. Leave empty and nothing changes. When it's reachable it takes priority over everything below; when it isn't, the chat silently falls back to the looping clips.

Avatar service URL — where avatar-service is running

Choose an avatar

None

Kate

James

More avatars are on the way — the chat falls back to the looping clips below whenever the GPU isn't reachable.

How to set this up

Rent a GPU (an RTX 4090 or L40S is plenty), run bash scripts/runpod_setup.sh in avatar-service/, then build the avatar once with python scripts/build_avatar_pack.py ./sources.

Paste the pod URL above and pick an avatar. Until the GPU is running, the chat keeps using the looping clips below.

Full walkthrough, costs and licence notes: docs/avatar-photoreal-gpu.md and docs/avatar-pack.md.

Video avatar (optional, free & photoreal, fallback)

Two short looping clips of a real person. The chat plays the idle clip and crossfades to the talking one whenever the agent speaks — photoreal, with no GPU, no per-minute cost and nothing to run out of. Used instead of the flat photo whenever the paid video avatar isn't available, and it takes priority over the 3D model below.

Idle loop — quiet, looking at camera Talking loop — optional; without it she simply doesn't change while speaking

How to make the two clips

Generate them from the agent photo (free) — SadTalker on Google Colab's free GPU turns one photo into both clips in ~10 minutes: blinking idle face + moving lips. Step-by-step guide: docs/avatar-photoreal-free.md in the repo (start with python scripts/make_avatar_audio.py).

Or record them — 10–20 seconds each on a phone, same seat, same framing, same lighting. Idle: look at the lens, blink, breathe. Talking: read anything at a natural pace. Start and end in the same pose so the loop doesn't jump.

Or generate via a trial — one HeyGen/D-ID free credit renders a talking clip you loop forever.

Or use stock — Pexels and Pixabay have free talking-head footage.

Mute them and keep them small (a few MB). Drop the files in content/agent/ and reference them as /agent-assets/<file>.mp4, or paste any public URL.

3D avatar model (optional, free)

A .glb head whose lips move with what the agent says — used whenever the paid video avatar isn't available, instead of the flat photo. Leave blank to keep using the photo.

To try it right now, paste this public test head: . For your own, create one free at Ready Player Me and add ?morphTargets=Oculus%20Visemes,ARKit to the URL, or export a .glb with ARKit blend shapes from any tool. The model must be served with CORS enabled.

Voice / tone

Describe how the agent should speak, e.g. "professional but friendly, concise".

Greeting text

The first message visitors see when the chat widget opens.

Greeting video URL (MP4, optional)

Short video shown in the chat header instead of a photo.

Default language

BCP-47 language tag, e.g. en, fr.

Demo booking URL

Your Calendly / Cal.com link — opens as an inline calendar in the chat and is used in follow-up emails.

Demo mode

What the AI shows when a visitor asks for a demo. In Slides mode it displays the specific slide image that matches the question; in Video mode it plays your demo video. Manage your slides & videos on the Demos page.

Branding

Brand colour

Sets the chat buttons, bubbles, and launcher. Pick a scheme below, or type any hex colour. Leave blank for the default blue.

Logo

Shown in the chat header instead of the agent name (wide/transparent PNG works best). PNG, JPG, GIF or WebP, up to 5 MB.

No logo

Font

A Google Fonts family name, e.g. Roboto, Poppins. Leave blank for the default.

Known pages (AI can redirect here)

Pages on your site the AI may send visitors to. When a visitor asks about a topic that matches one (e.g. pricing), the AI answers, then—after it finishes speaking—takes them to that page. Use a path on the site where the widget is embedded, e.g. /pricing (not a full https:// link).

Per-page playbooks

Override the greeting and how fast the chat opens, based on the visitor's page or campaign. The first matching rule wins; pages with no match use the defaults above.