ATC-ASR 110M
Speech-to-text tuned on air-traffic radio. 0.6% word error rate on real ATC recordings, about 0.2 s on a CPU. Clean-up rules normalise numbers and fillers before parsing.
01 / 07 · Personal · flagship · May – Nov 2026
Voice air-traffic control at SFO, running on small models I trained. No LLM, no GPU at run time.
The problem
You are ground, tower or approach. Key the mic, speak a clearance; pilots read it back and fly it.
I wanted that to work on an ordinary laptop, in a browser tab. So I trained my own small models for every step that listens, decides or speaks. The model only ever writes a typed command line like UAL214 C 5000. Everything else is rules, a game engine and a safety gate.
A simulated, in-browser demo of the pipeline. Rules-based stand-ins play the part of my models here; the real ones run at openatc.aeon-labs.site.
2 · Choose a clearance
Heard
—
Command line
—
Gate
idle
Pilot readback
Select an aircraft and transmit.
How it works
Speech-to-text tuned on air-traffic radio. 0.6% word error rate on real ATC recordings, about 0.2 s on a CPU. Clean-up rules normalise numbers and fillers before parsing.
A 2M-parameter GPT-style transformer trained on 205,000 simulated situations across 11 airports, with a custom 1,349-token BPE where every ATC word is one token. It runs int8 in a Web Worker in 0.1–0.2 s, and only when the rules can't parse.
Every command passes a verifier before the engine sees it: send, ask to confirm, or "say again". It cut wrong auto-sends from 19% to 0.9%.
Phraseology turns the command into a proper readback, and an 8.5 MB TTS model speaks it at 6× real time in WASM, in the browser.
Numbers
0.6%
word error rate on real ATC recordings · 110M ASR · ~0.2 s on CPU
GRPO with the game engine as the reward · exact match
p = 0.013 against the SFT control
2M
parameters in S1-2M, trained from scratch
205,000
simulated situations across 11 airports
1,349
tokens in a custom BPE · every ATC word is one token
19% → 0.9%
wrong auto-sends after the safety / verifier gate
74 → 44
wrong-aircraft errors after GRPO
4.5× / 7×
faster decoding from a hand-written KV cache / prefix caching
8.5MB
Paradee-8M pilot voices · 6× real time in WASM
62ms
on-device streaming speech in the Flutter phone app
14 Nov 2026
first public release · MIT licence · models on Hugging Face
The reel
Move over the stack to turn it; scroll to scrub through it. Each slice is a frame of the reel, stacked in depth.
Drag the strip · placeholder screenshots






All gallery images are placeholders. Swap for real SkyControl screenshots.
Stack
First public release on 14 Nov 2026, MIT licensed. Models are on Hugging Face.