Skip to main content
Éist

Éist research · 2026-09-15-v1

Piper performance in Éist

Piper VITS through sherpa-onnx 1.12.40, cache version 5. These are observational results from Éist installations with analytics enabled, not a general benchmark of every Piper implementation.

Platform summary

Piper on android

0.247 RTF

p10–p90: 0.115–0.782
297 installations · 11,193 active health samples
Éist 1.3.21 · piper-v5-sherpa-1.12.40

Piper on ios

0.115 RTF

p10–p90: 0.088–0.23
293 installations · 16,620 active health samples
Éist 1.3.19 · piper-v5-sherpa-1.12.40

Qualifying device cohorts

Only cohorts with at least 100 active health samples and 10 installations appear. Lower RTF is faster.

Piper device cohorts
Engine Device Observed OS Median RTF p10–p90 Installations Health samples
Piper iPhone18,2 iOS 26.6–27.0 0.09 0.088–0.103 11 193
Piper iPhone18,1 iOS 26.3–26.6.1 0.098 0.089–0.192 10 360
Piper iPhone17,2 iOS 26.5.2–26.6.2 0.101 0.095–0.21 11 234
Piper iPhone18,3 iOS 26.6–27.0 0.101 0.086–0.162 14 969
Piper iPhone15,2 iOS 18.5–26.6.2 0.102 0.093–0.317 15 222
Piper iPhone17,1 iOS 18.6.2–27.0 0.103 0.085–0.175 17 512
Piper iPhone16,1 iOS 18.7.8–26.6.1 0.106 0.088–0.174 15 373
Piper iPhone16,2 iOS 26.5–27.0 0.11 0.093–0.129 11 168
Piper iPhone17,3 iOS 26.3–27.0 0.115 0.095–0.186 27 2,399
Piper iPhone15,4 iOS 26.3.1–27.0 0.122 0.097–0.214 14 1,428
Piper iPhone15,3 iOS 26.6–27.0 0.123 0.092–0.238 12 138
Piper iPhone14,7 iOS 18.7.2–27.0 0.133 0.1–0.249 13 2,468
Piper iPhone14,5 iOS 18.5–26.6.2 0.153 0.113–0.274 21 399
Piper iPhone12,1 iOS 18.2–26.6.2 0.196 0.166–0.797 16 260

Full dataset, filters and methodology →