Box v1.0.6

### Box v1.0.6

New: On-Device Image Generation

First stable release of on-device image generation. Previous builds had crashes and instability in the Stable Diffusion
pipeline — v1.0.6 resolves these and is the first version we'd consider ready for daily use.

- Image generation time dropped from ~27 minutes to under 4 minutes — earlier builds required 20 steps with base SD 1.5;       

LCM-SSD-1B (recommended) produces quality results in just 4 steps thanks to consistency distillation, combined with the CPU
optimisations below

• Added Image Gen — generate images from text prompts fully on-device using Stable Diffusion
• 6 models available to download, powered by stable-diffusion.cpp:
  • LCM-SSD-1B Q4_K (~2.2 GB) — recommended, fast SDXL-class results in 4 steps
  • SDXL-Lightning 4-step Q4_0 (~2.8 GB) — ByteDance distillation, high quality in 4 steps
  • SDXL-Turbo Q4_0 (~4.2 GB) — vivid results in 1–4 steps
  • SDXL Base Q4_0 (~3.9 GB) — full SDXL at native 1024² resolution
  • SD 1.5 Q4_0 (~2.1 GB) — classic reliable all-rounder
  • SD 1.5 Q8_0 (~4.0 GB) — higher precision SD 1.5
• Adjustable steps, CFG scale, negative prompt, and image size (256² up to 1024²)
• Save generated images directly to your gallery
• Import your own GGUF model files from device storage
• Fixed crash (SIGSEGV) on second generation — was a use-after-free in the sd.cpp context; context is now reloaded before each
  generation

### Performance

• Enabled ARM dotprod + FP16 CPU kernels for all ggml-based inference (Stable Diffusion, SmolLM,llama.cpp) — these were silently disabled
  at build time due to cross-compilation defaults
• Upgraded ggml release builds from -O2 to -O3 optimisation
• Enabled flash attention in Stable Diffusion — reduces memory pressure during sampling
• Compiled in experimental Vulkan GPU backend for Stable Diffusion (auto-falls back to CPU if unsupported)

Voice Input / Audio Scribe

• Removed Whisper Tiny — was hanging on transcription; Whisper Base is now the smallest option

General

• Model cards now show descriptions when expanded — tap any model card to see details and recommended settings
• All Image Gen model cards include plain-English descriptions and recommended CFG/step settings

Two variants available:

• Box_v1.0.6_Main_Signed_Release.apk — stock Android 15 +
• Box_v1.0.6_custom-rom-support_Signed_Release.apk — GrapheneOS / custom ROMs without Google Play Services

APK size reduced from ~890 MB to ~550 MB — native libraries are now compiled for arm64 only, dropping unused x86 and 32-bit
ARM builds. All devices that can run Box (Android 15+) are arm64.

Box 1.0.5

Main — v1.0.5

New Models

• Gemma 4 E2B & E4B model files refreshed — updated commit hashes from HuggingFace.

New Features

Audio Scribe
Record audio directly in the app or import a WAV file. Whisper transcribes it on-device, optional speaker diarization labels each speaker, then
the LLM can summarise, analyse, or answer questions about the content. Entirely offline.

Ask Audio (multimodal chat)
Send a recorded audio clip or WAV file directly into AI Chat with Gemma 4 E2B / E4B. The model hears and responds to the content.

Text-to-Speech screen
Dedicated TTS tab for on-device voice synthesis using system TTS or an imported Piper/ONNX model.

Real-time voice reply updated
Enable in Settings to have the AI speak its reply sentence by sentence as it generates, rather than waiting for the full response. Works with
Android system TTS or an imported Piper model.

TTS voice picker
Settings → TTS Voice — choose which installed offline system voice is used for AI replies.

AI Chat shortcut
Long-press the Box icon → AI Chat. Navigates directly into chat even from a cold start.

In-app update checker
Settings → Check for updates. Fetches the latest release from GitHub and shows a direct download button if a newer version is available.

Model import from list
Whisper and TTS models can now be imported directly from the model list screen without needing a model already downloaded.

Performance

• Speculative decoding / MTP working — capability is now checked against the model file itself, not the allowlist. Gemma 4 E2B reaches 66–91
  tok/s with GPU + speculative decoding on real conversation text vs ~52 tok/s plain GPU (Galaxy S26 Ultra).
• Sustained Performance Mode — CPU/GPU clocks locked during inference. No more thermal throttle mid-conversation.
• Benchmark speculative decoding toggle — benchmark screen now exposes the toggle for models that support it.

Bug Fixes

• Fixed app shortcut navigating to home screen instead of chat on cold start.

---

### custom-rom-support — v1.0.5

All changes from Main above, plus:

New Models

Same model set as Main. Accelerator order includes NPU (gpu,npu,cpu) for Tensor devices on supported ROMs.

Performance

• Speculative decoding and Performance Mode as above.
• GPU is the recommended accelerator on Snapdragon. NPU path on Snapdragon is untested on custom ROMs — falls back to GPU automatically.

custom-rom-support specific

• Piper TTS (Amy) available as a built-in download in the TTS tab — no third-party TTS app needed on de-Googled ROMs.
• No Google Play Services dependency — AICore/Firebase paths are bypassed.
• TTS voice reply works out of the box with the bundled Piper engine.

Notes

This build is for GrapheneOS, LineageOS, CalyxOS, and other custom ROMs without Google Play Services. If you are on stock Android (Pixel,
Samsung, etc.) use the Main APK. If you previously installed Main, uninstall it before switching — the package ID is the same and you will
get a signature conflict.

Box v1.0.4

● main branch — v1.0.4

What's new in v1.0.4

Bug fixes

• Fixed missing GPU option on Pixel 10 Pro Fold — GPU is now available as an accelerator alongside CPU (NPU/TPU works on custom OS roms)

Box 1.0.3

v1.0.3 — Stock Android

Bug Fixes

• Images now persist across sessions — Photos sent in a conversation are saved to local storage and correctly restored when returning to
  or reopening a conversation. Previously, images would disappear after navigating away or restarting the app.

custom-rom-support v1.0.4

custom-rom-support — v1.0.4

What's new in v1.0.4

Bug fixes

• Fixed missing GPU option on some devices. — GPU is now available as an accelerator alongside TPU and CPU
• Fixed accelerator setting resetting to GPU after app is fully closed — your chosen accelerator (TPU, GPU, or CPU) now persists across app restarts

custom-rom-support-v1.0.3

v1.0.3 — Non-Stock Android (GrapheneOS / LineageOS / CalyxOS)

Bug Fixes

1 - Images now persist across sessions — Photos sent in a conversation are saved to local storage and correctly restored when returning to
or reopening a conversation. Previously, images would disappear after navigating away or restarting the app.
2 - Benchmark no longer crashes when NPU is unavailable — Running the benchmark on devices without NPU/AICore support (e.g. older Tensor
chips on GrapheneOS/LineageOS no longer causes a crash. The backend now correctly falls back to CPU in this case.
3 - Accelerator setting no longer resets after navigation — Changing the accelerator (CPU / GPU / NPU) in model config is now saved
correctly. Previously the setting would silently revert to its default value after navigating away and returning.

Huge thanks to aryoda for pointing out these bugs !

---

Custom Rom Support v1.0.2

I have now created a separate branch called custom-rom-support, along with a corresponding release section specifically for users on third-party operating systems.
If you are using a custom ROM, please use the custom-rom-support
branch/release instead of the main branch. This branch supports TPU/NPU
acceleration on Tensor devices; however, Snapdragon acceleration
remains untested.
Please expect broken features if you are using a custom ROM and running the current release or branch from main. A separate APK and branch (custom-rom-support)
are now available for users on third-party Android operating systems,
including but not limited to LineageOS, GrapheneOS, and CalyxOS.
Note:
The primary reason for these limitations is that third-party operating
systems typically lack AICore and system-level Text-to-Speech (TTS)
components. As a result, features such as voice-to-voice mode and
NPU/GPU acceleration are either unavailable or significantly impaired on
these ROMs.

• Stock Android users should continue using the standard main branch build — this build is
  not needed and adds no benefit on stock Android
  • Amy (Piper TTS) must be downloaded from the Voice tab before voice reply works offline

custom-rom-support — Release Notes

Custom ROM Support (GrapheneOS · LineageOS · CalyxOS)

This release brings full voice-to-voice AI chat support for custom Android ROMs that ship
without Google services (AICore, Google TTS, Google STT).

---

What's New

Voice-to-Voice on Custom ROMs

• Microphone button now works on GrapheneOS and other de-Googled ROMs using the built-in
  Whisper speech recognition engine
• Voice Activity Detection (VAD) automatically sends your message after 1.5 seconds of
  silence — no need to press a button to stop recording
• Speaker button now works on custom ROMs using the Amy (Piper) TTS engine — auto-downloads
  and initialises on first use
• Real-time voice reply now streams speech sentence-by-sentence as the AI generates,
  matching stock Android behaviour
• Amy TTS pre-loads when AI Chat opens so real-time playback is ready from your first
  message
• Microphone automatically restarts after the AI finishes speaking, enabling continuous
  hands-free conversation

Performance

• AI Chat inference is now fast on Tensor G5 devices running GrapheneOS — routes through
  Android NNAPI to reach the TPU without requiring AICore

Bug Fixes

• Fixed Amy TTS model download failing on GrapheneOS due to a HuggingFace redirect URL bug
• Fixed mic not auto-restarting after AI response on custom ROMs

Settings

• Added "Non-Stock Android" notice in Settings clarifying this build is intended for custom
  ROM users

Box

v1.0.2 — Voice Mode & Vision Talk / NPU/TPU Acceleration

New Features

Free Talk — Hands-Free Voice Conversation

• Continuous speech-to-speech AI conversation with no button press between turns
• Tap the mic button to start, speak naturally, AI replies and listens again automatically
• Real-time TTS: each sentence is spoken as it generates rather than waiting for the full response
• Enable Real-time voice reply in Settings to turn it on

Vision Talk — Live Camera + Voice AI

• Stream your back camera live to the AI during a voice conversation
• Point at anything and ask about it out loud — AI sees the current frame and speaks the answer back
• Fully hands-free: mic → AI sees scene → AI speaks → mic restarts automatically
• Requires a vision-capable model (Gemma 4 E2B or E4B)

TTS Voice Picker

• Choose your preferred offline system voice in Settings
• Only locally installed voices shown (network-dependent voices filtered out)
• GrapheneOS / de-Googled ROM users: install RHVoice or eSpeak NG from F-Droid

LaTeX Math Rendering

• Greek letters, operators, fractions, integrals, summations rendered inline as Unicode
• Works automatically in assistant messages

Improvements

• GGUF model context size now scales with file size to prevent hangs on Android 17 Beta 4 (MemoryLimiter) — large models use a reduced KV cache automatically
• Removed QNN Hexagon skeleton .so libraries ( will be added back next release to support snapdragon acceleration )
• Removed interactive map skill

Bug Fixes

• Fixed model initialization hanging indefinitely — now times out after 30 seconds with a clear error
• Fixed app crash on invalid task ID (force unwrap replaced with safe exit)
• Fixed real-time TTS stalling on responses with no sentence punctuation (code blocks, URLs now flush correctly)
• Fixed TTS audio playback wiring in AI Chat

Box

New Inference Engines

Local Diffusion (stable-diffusion.cpp)
On-device image generation powered by stable-diffusion.cpp. Runs Stable Diffusion 1.5 in GGUF format, fully offline. Configurable steps, CFG scale, seed, and image size presets. Import
your own GGUF diffusion models.

Voice (whisper.cpp)
On-device speech-to-text powered by whisper.cpp. Record audio or pick a WAV file, transcribe offline. Supports Whisper Tiny through Small in multiple languages. Audio never leaves the
device.

NPU / TPU Acceleration
All Qualcomm Hexagon NPU variants (Snapdragon 8 Gen 2 / 8 Gen 3 / 8 Elite / newer), Google Tensor TPU (Pixel 8–10), and MediaTek NPU bundled in a single APK. Select NPU in the model
accelerator dropdown — Box auto-detects the chip at runtime.

---

Security

• Biometric App Lock — Optional lock via BiometricPrompt, re-prompts on every foreground
• Encrypted Chat History — All conversations persisted to SQLCipher-encrypted Room database (AES-256 at rest)
• Passphrase isolation — BiometricEncryptionManager + PassphraseHolder keep the DB key in memory only while authenticated
• Hard Offline Mode — Toggle in Settings forces full airgap; all download attempts are blocked
• Security Audit Log — On-device append-only log of security-relevant events
• Prompt sanitisation — SecurityUtils.sanitizePrompt() strips control characters before inference and persistence
• Tapjacking protection — filterTouchesWhenObscured on the chat scaffold

---

Chat

• Conversations persist across sessions and resume where you left off
• Chat History screen — browse, resume, or delete past conversations
• Multimodal input in AI Chat with Gemma 4 E2B / E4B — attach documents, record audio, take photos
• Improved message input and scroll behaviour

---

Agent Skills

New built-in skills:

• Budget Tracker
• Password Generator
• Translator

Updated skills: Calculate Hash, QR Code

Removed: Kitchen Adventure, Text Spinner

---

Model Management

• Import any GGUF file from local storage at runtime
• Set display name and accelerator (CPU / GPU / NPU) at import time
• Fixed: models appearing multiple times after screen rotation (deduplication guard in loadModelAllowlist)
• Fixed: Voice and Local Diffusion showing 0 models after allowlist reload

---

• Gradle 9.4.1 compatibility
• stable-diffusion.cpp and whisper.cpp added as native submodules
• llama.cpp updated
• Plus a whole lot more !

v1.0.0

Box v1.0.0 — Initial Release

Box is a security-hardened Android app for running large language models fully on-device. Forked from Google AI Edge Gallery with significant privacy and usability improvements.

Features

• On-device LLM inference via LiteRT and llama.cpp
• GGUF model support — import any compatible GGUF model from local storage
• Accelerator selection — choose CPU, GPU, or NPU per model
• Encrypted chat history — all conversations stored with SQLCipher encryption
• Biometric lock — optional fingerprint/face authentication to access the app
• Offline mode — block all network requests, run entirely air-gapped
• Chat persistence — conversations are saved and automatically resumed per model
• Copy to clipboard — long-press any AI response to copy it

Privacy

• No telemetry or data collection
• All inference runs locally on-device
• Chat history never leaves the device
• FLAG_SECURE prevents screenshots and screen recording

Notes

• Gemma models are subject to the Gemma Terms of Use
• GGUF import requires models compatible with llama.cpp