1# What the app is built from
2
3## The pixel icons (`third-party/pixel-icons`, drawn from `PixelIconSet.kt`, generated by `tools/build-core.sh`)
4
5[shuqikhor/pixel-icons](https://github.com/shuqikhor/pixel-icons) by shuqikhor: the pictures on the child's memory cards and menu, the ones listed in `crates/whiskers-icons/allowlist.txt`.
6
7## The offline voice (`tools/fetch-offline-voice.sh`; none of it is committed except `Tts.kt`)
8
9| Part | What |
10| --- | --- |
11| Engine | [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx) 1.13.8, `libsherpa-onnx-jni.so`, and its Kotlin API file `Tts.kt` (committed under `app/src/main/kotlin/com/k2fsa/sherpa/onnx/`) |
12| Runtime | ONNX Runtime, `libonnxruntime.so` (shipped inside the sherpa-onnx release) |
13| Phonemiser | eSpeak NG, linked into sherpa-onnx, and its `espeak-ng-data` |
14| Voice | Piper `en_US-ljspeech-medium`, a female US English voice trained by Bryce Beattie on the LJ Speech dataset by Keith Ito, repackaged for sherpa-onnx as `vits-piper-en_US-ljspeech-medium-fp16` |
15
16Sources, read 2026-10-04: the model card in the voice archive and <https://keithito.com/LJ-Speech-Dataset/>.