New iOS-first companion (Expo SDK 54 + NativeWind v4) with three tabs:
Captures (the hero — floating gold mic, live mic-meter waveform,
expand-row playback), Generate (profile picker + speak + autoplay +
recent), and Voices (searchable profile list).
Pairing (V0): backend mints a one-time token, mobile scans/pastes the
voicebox:// URL, server returns a long-lived bearer it stores only as a
SHA-256 hash. Bearer-or-loopback auth applied to every user-data router
so binding 0.0.0.0 doesn't leak existing endpoints. Loopback callers
(the desktop app) keep their friction-free access.
Desktop Settings → Mobile pane: live host picker (LAN / Tailscale auto-
detected via the App-bundle binary path on macOS), QR rendering,
5-minute expiry countdown, copyable URL fallback, paired-device list
with revoke. Auto-closes when a new device pairs.
just dev now binds the backend to 0.0.0.0 so paired phones can reach
it — and just setup-python pins mlx-audio==0.4.1 + mlx-lm so fresh
Apple Silicon worktrees get a working STT path on first install.
Address CodeRabbit review feedback and user-reported GPU acceleration failure:
- Use shared manual_seed() in chatterbox, chatterbox_turbo, and luxtts
backends so XPU (and future accelerators) get proper device seeding
- Add XPU branch to _get_gpu_status() so startup log reports Intel Arc
GPUs instead of 'None (CPU only)'
- Add XPU VRAM reporting and correct backend_variant fallback in the
/health endpoint
- Switch justfile GPU detection from Get-WmiObject to Get-CimInstance,
simplify the Arc regex to match 'Arc' (not 'Intel.*Arc'), log
detected GPUs, and print manual install instructions on miss
Resolves the root cause where IPEX was silently not installed due to
WMI detection failure, causing CPU-only fallback on Intel Arc systems.
Auto-detect Intel Arc GPUs during Windows setup and install PyTorch
with XPU support + intel-extension-for-pytorch. Enable allow_xpu=True
on all TTS backends (Chatterbox, Chatterbox Turbo, Hume TADA, LuxTTS)
that previously only supported CUDA. Add shared empty_device_cache()
and manual_seed() helpers in base.py to handle XPU memory management
and reproducible seeding alongside CUDA.
Upgrade CUDA toolkit from 12.6 (cu126) to 12.8 (cu128) for proper
RTX 50-series (Blackwell) GPU support. Users with RTX 5070/5080/5090
were reporting CUDA detection failures with cu126.
Also fix the GPU Acceleration settings panel where the 'Switch to CPU
Backend' button was unreachable — it was inside a conditional block
that required !isCurrentlyCuda, making it impossible to switch back
to CPU once running on CUDA.
Closes#315
- Wrap download/verify/extract in try/finally so .download-*.tmp is
always deleted, even on mid-download or extraction failures
- Fix justfile build-server-cuda to use sh.voicebox.app (production path)
Integrates HumeAI's TADA (Text-Acoustic Dual Alignment) speech-language
model as a new TTS engine. TADA uses a novel 1:1 token-audio alignment
that produces coherent speech over long sequences (700s+).
Two model variants:
- tada-1b: English-only, ~4GB, built on Llama 3.2 1B
- tada-3b-ml: 10 languages, ~8GB, built on Llama 3.2 3B
Backend uses the Encoder for voice prompt encoding with caching, and
TadaForCausalLM with flow-matching diffusion for generation. Supports
bf16 inference on CUDA, forces CPU on macOS (MPS compatibility).
Installed with --no-deps due to torch>=2.7 pin conflict; descript-audio-codec
and torchaudio added as explicit sub-dependencies.
chatterbox-tts 0.1.6 pins numpy<1.26 and torch==2.6 which are
incompatible with Python 3.12+. Install with --no-deps and list
its sub-dependencies explicitly in requirements.txt.
Also removes HFProgressTracker from chatterbox backend to avoid
'generator didn't stop after throw()' errors from tqdm patching.
Adds 'just' as the recommended dev tool: 'just setup' for one-time
install, 'just dev' to run backend + frontend in one terminal.
Updates CONTRIBUTING.md to document just as the primary setup method.
James Pine