Benchmarks

How fast is Parakey?

Parakey keeps its latency claims tied to a reproducible benchmark in experiments/swift-bench/. Numbers below are p50 across five trials per backend, first inference excluded.

Setup

Environment

MachineMac mini M4, 10 cores, 16 GB.
OS and toolchainmacOS 26.4.1, Xcode/Swift 6.3.
TrialsFive per backend per clip. First inference after model load excluded from p50.
AudioGenerated 16 kHz mono Float32 WAV clips, all tested against the same backends.
p50 latency

Results

Clip Duration FluidAudio on ANE Prior GPU path Speedup
short-clean 2.50 s
92.4 ms
145.4 ms
1.57×
medium-clean 3.99 s
96.1 ms
176.3 ms
1.83×
disfluent 5.31 s
94.1 ms
185.9 ms
1.97×
longer-technical 9.49 s
152.4 ms
300.9 ms
1.97×

Machine-readable results: benchmarks/results.json. Reproduction docs: experiments/swift-bench.

Reading the numbers

Interpretation

Latency

The ANE path is consistently faster than the prior GPU path on these clips, with p50 results around 92-152 ms.

Accuracy

Both backends produced essentially identical transcripts on the synthetic test audio, including the same TTS artifacts.

Power

The benchmark measures compute latency, not energy. Power measurement remains a future bench improvement.