Licenses and Model Notices

Release Covered By This Page

This page records the signed English Voice Coach Android release 1.0.0+1, source commit cde722d. The audited App Bundle SHA-256 is 9e7e2a0f6ac937b98faa6174dec2fe375fb8f5b7f39ccabd6d2dfcf46a616749.

The App Bundle includes an offline Flutter license registry. In the app, open Settings, choose Licenses and model notices, and then choose Flutter licenses to read the complete package notices shipped with the release.

Third-Party Technology

English Voice Coach uses Flutter and Dart, AndroidX and Kotlin, Google ML Kit text recognition, LiteRT and LiteRT-LM, Sherpa-ONNX, Microsoft ONNX Runtime, OpenAI Whisper and whisper.cpp, Kokoro voice files, and other packages listed in the app's embedded license registry.

Apache 2.0 components are distributed under the Apache License, Version 2.0. MIT and BSD-style components are distributed under their respective notices. Use of a product or project name is attribution only and does not imply endorsement.

Gemma 4 Review

English Voice Coach uses the Gemma 4 E2B instruction-tuned model in LiteRT-LM format: gemma-4-E2B-it.litertlm, from the Hugging Face repository litert-community/gemma-4-E2B-it-litert-lm, based on google/gemma-4-E2B-it by Google DeepMind.

The current public source labels the Gemma 4 model Apache 2.0, and Google's Gemma 4 model card/license page lists Apache 2.0. This allows use in English Voice Coach when Apache 2.0 notices are included. The expected SHA-256 for this app is 181938105e0eefd105961417e8da75903eacda102c4fce9ce90f50b97139a63c. The first release uses direct Hugging Face download with hash verification.

English Voice Coach is not affiliated with, sponsored by, or endorsed by Google, Google DeepMind, Hugging Face, or the LiteRT-LM project. Model outputs may be incomplete or incorrect and are provided as language-practice suggestions.

Speech Recognition

English Voice Coach uses converted Whisper model files from the whisper.cpp model repository for local speech recognition. OpenAI Whisper and whisper.cpp are MIT-license components. The files are pinned to repository revision 5359861c739e955e79d9a303bcbc70fb988958b1; the app release record preserves SHA-256 values for the tiny, base, and small English files.

Offline Voice

English Voice Coach uses Sherpa-ONNX 1.13.1, Android native packages 1.13.2, and the Kokoro English archive kokoro-en-v0_19.tar.bz2 for offline voice playback. These are Apache License 2.0 posture components. The archive SHA-256 is 912804855a04745fa77a30be545b3f9a5d15c4d66db00b88cbcd4921df605ac7.

The Sherpa-ONNX Android package bundles Microsoft ONNX Runtime. The exact release binary exposes version marker 1.24.3. ONNX Runtime is provided under the MIT License, copyright Microsoft Corporation.

App And Android Dependencies

Direct Dart packages in this release are archive 4.0.9, sherpa_onnx 1.13.1, and url_launcher 6.3.2. The resolved Android graph includes AndroidX Core 1.17.0, ML Kit text recognition 16.0.1, LiteRT-LM Android 0.11.0, and Kotlin standard library 2.2.21, with their transitive dependencies.

The archive 4.0.9 package is MIT licensed and also preserves supplementary notices for imaya zlib.js, JCraft JZLib, bzip2/libbzip2 by Julian Seward, and Pointy Castle/Bouncy Castle-derived code. Complete Flutter/Dart package text is available through the app's Flutter licenses screen.

License Sources

Source records for the current stack: Gemma 4 model card, Gemma 4 Apache 2.0 license, Gemma 4 LiteRT-LM repository, Kokoro model card, OpenAI Whisper MIT license, whisper.cpp MIT license, Sherpa-ONNX Apache 2.0 license, ONNX Runtime MIT license, and LiteRT Apache 2.0 license.

License Text

The full Apache License 2.0 and Flutter/Dart package terms are stored in the signed app's offline notice registry. The model notice screen preserves the Whisper/whisper.cpp notice and the Apache component attribution. The release record additionally preserves the ONNX Runtime MIT notice and the archive supplementary notices.

Read the complete supplemental notice text for this release. For an inaccessible notice or another format, contact support@barbutsa.com.