0
Car wired and talking today
0
Target response latency
0
Cars in the first pilot
0
Cars in the learning phase

One is what exists. The rest are the gates we're building toward, in order.

Running today

What's already on the road.

The full pipeline of listening, thinking and talking back runs end to end on the prototype hardware right now.

Wake word & voice pipeline
Wake detection into streaming speech-to-text, language model and speech, with overlapped playback so EXCAR starts talking before it has finished thinking.
Live
Music, maps & phone actions
Spotify by voice, navigation handed to the phone with turn-by-turn directions, and reminders. No screen touched.
Live
Proactive alerts
EXCAR speaks first when it matters. A driver-controlled switch decides how chatty it is allowed to be.
Live
iOS companion app
Setup, personality settings, and reviewing or clearing what EXCAR remembers. On TestFlight now.
Beta
Automated test suite
Voice pipeline, memory, routing and integration layers under automated tests. Unglamorous, and the reason the prototype survives being touched.
Live
The road ahead

Six stages. Each one closes something.

We'd rather show you what has to be true to call a stage done than quote a completion percentage nobody can check. Pick a stage.

Stage 01 · In progress

Close the physical unknowns before we scale anything.

Measurement, mechanical design, electrical and power behaviour, thermal limits, cabin acoustics, the Bluetooth OBD link, and testing in the vehicle rather than on a desk.

Why it matters

A car interior is a genuinely hostile place for electronics: heat, vibration, noise, and a battery with other priorities. Every unknown we close here is one we don't pay for later, in someone else's car, at ten times the cost.

What closes it
  • Power and thermal behaviour measured across ignition cycles
  • Cabin acoustic performance characterised while driving
  • Bluetooth OBD link verified against supported vehicles
  • Mechanical envelope fixed and documented
  • Findings written up as a verification record, not folklore

Beyond stage 05 is opening EXCAR to everyone who wants one. We're not putting a date on that, because the honest answer is that it depends on how the fifty cars behave.

Two tracks, one destination

The software and the hardware are the same plan.

What we learn from real drivers defines the board. What the board can carry defines the intelligence it serves. Neither track finishes alone.

Intelligence
Working voice loop
Context evaluation
EXCAR LLM
A character we own
Hardware
EXCAR One prototype
Verified system
Custom board
EXCAR Link
Where they meet

Smaller hardware. Deeper relationship.

Under the hood

Built to work in any car, starting with one.

EXCAR's software is split into a car-agnostic core and small per-vehicle plugins, so supporting a new car model is an addition, not a rewrite.

Core

Listens, thinks, speaks

Wake word detection, speech-to-text, the conversation engine, text-to-speech, and memory, identical in every car, regardless of make or model.

Plugin layer

One core, every make

Per-vehicle integration lives in a small plugin, so supporting a new make or model is an addition, not a rewrite.

EXCAR LLM

One model, trained for the car

Every response runs through a cloud language model tuned for this environment. We're training our own, EXCAR LLM, from open weights, so the character behind every conversation is ours.

Want to ride along while we build it?

Join the waitlist for the first pilot, or follow along as EXCAR moves from one car to a fleet.