01 / API
API
- ▸Premium quality
- ▸Ease of use
- ▸Built for scale
REST + Python SDK. Drop-in integration for NORTH Realtime Avatar. Built for production workloads at any scale.
Realtime AI
avatars
that talk back.
Turn any photo into a real-time, lip-synced video agent your users can actually talk to. Photorealistic, realtime, and ready for your product.
Compatible with
Logos are customer-provided integrations. NORTH is not affiliated with or endorsed by these providers.
Our avatar
Curated outputs
See them come alive
A tighter reel of generated avatars so visitors understand the product before they hit the interactive demo.
Hover or tap to preview motion. Audio is optional.
Using ElevenLabs voices. Hover any avatar to preview motion.
Speaking…
AI professional
Speaking…
AI professional
Speaking…
AI professional
Speaking…
AI professional
Speaking…
AI professional
Speaking…
AI professional
Speaking…
AI professional
Speaking…
AI professional
Speaking…
AI professional
Speaking…
AI professional
Speaking…
AI professional
Speaking…
AI professional
Speaking…
AI professional
Speaking…
AI professional
◆ Plugs into your stack
Your LLM.
Your voice.
Our face.
NORTH renders the avatar; you keep control of the brain, the voice, and where the video goes. See the API docs.
No session caps. No per-call time limit. Production tiers are not boxed into fixed RPM ceilings.
Run an avatar for as long as your app needs. Bill by the second.
Any LLM, via your API key
Your fine-tuneWe don't lock you into a model. Plug yours in and we render the face.
Any voice
CartesiaAzureYour ownWe lip-sync to phoneme timing, so any TTS, any language.
Anywhere you stream
WebRTCYour client
Your clientDrop a NORTH avatar into a real meeting bot or your own product.
Logos are customer-provided integrations. NORTH is not affiliated with or endorsed by these providers.
Product surfaces
Generate clips,
or run live avatar calls.
Offline mode turns a face and script into a polished MP4. Realtime mode lets users talk to an AI avatar live with voice, video, and realtime responses.
⌘ 00 / Deployment
Built to ship.
Built to scale.
Whether you're integrating via REST, streaming over WebRTC, or shipping a polished playground experience, our models work wherever you do.
NORTH Realtime Avatar
4 surfaces · 1 model family
Get started →↗
02 / Realtime
Realtime
- ▸WebRTC, Zoom, Meet
- ▸Any LLM you bring
- ▸No session caps
Stream photorealistic, lip-synced avatars over WebRTC with adaptive bitrate. Identity transfer from a single reference photo.
03 / Enterprise
Enterprise
- ▸Dedicated capacity
- ▸Custom training
- ▸SLA & support
For larger organizations adding the NORTH Realtime Avatar API to their products and services with dedicated capacity and support.
04 / Playground
Playground
- ▸No code required
- ▸Iterate on prompts
- ▸Realtime demos
Experiment with the NORTH Realtime Avatar family from the hosted playground. Test ideas, iterate on prompts, and ship.
◆ Built for Enterprise
Procurement-ready, on day one.
SCIM, SSO, dedicated GPU capacity, passthrough by default, and a real audit trail. Enterprise contracts only.
SCIM / SAML SSO
Enterprise IAM via your IdP. Provision and de-provision users programmatically; no per-seat fees.
Zoom + Google Meet
Drop a NORTH avatar into a live Zoom or Meet call via standard meeting-bot frameworks (LiveKit, Recall.ai). One API request, your existing room.
Passthrough by default
NORTH receives audio and returns video. Your prompts, customer data, and knowledge base never leave your stack.
Dedicated capacity + SLA
Reserved GPU capacity, guaranteed throughput, and a 99.9% uptime SLA on Enterprise contracts.
Audit log + security review
DPA, sub-processor list, and security questionnaire support for procurement.
◇ Stuff people ask
Real questions from real DMs.
I'm building this site myself, so this is the running list of the questions that actually come up, in DMs, intro calls, partner emails. If yours isn't here, ask me and I'll add it.
Q · 01
Who is NORTH for?
Anyone shipping a product where a face needs to talk, devs, founders, agencies, enterprise. Specifically nota consumer app: we're the engine other products plug into. If you want to log in and post short-form video to social, there are great studio products for that. If you want a talking face inside yourproduct, you're in the right place.
Q · 02
What's actually included in the price?
Just the avatar, the face talking. You bring your own TTS (ElevenLabs, Cartesia, OpenAI TTS) and your own LLM (OpenAI, Anthropic, Mistral, or a fine-tune). It keeps you in control of voice, prompt, and cost. Want a turnkey bundle instead? Read on.
Q · 03
Can you bundle TTS + LLM in one invoice?
Yes, via partnership. We've negotiated rates with ElevenLabs and the major LLM providers, so for committed volume we can pass through cheaper than retail and bill it on one line. Email me if it sounds useful.
Q · 04
What can I actually build with this?
Realtime support agents, sales SDRs, NPCs, language tutors, virtual companions, async sales outreach at scale, training videos, onboarding flows, news anchors. Rough rule: if a face talking to a person makes the experience better, you're in the right neighborhood.
Q · 05
Do you do custom integration?
Yes. From a shared Slack channel and roadmap input, all the way to embedded engineering and fine-tunes for enterprise. We're a small team, that means we actually move fast on real partnerships.
◇ One model family · Endless surfaces
Build a tutor.
One avatar foundation model. Every application that needs a face, a voice, and a presence, shipped on your stack.