v0.4.4

antonibigata/keysyncv0.4.4Apr 21, 2026by github-actions[bot]

AI Summary

Reverts inference-path guards to fix generation failures for online users, while maintaining load-time offline guards.

Key Highlights

Fixes generation failure for online users by reverting inference guards
Known caveat: brief pauses for offline users during metadata timeouts (~30s)

New Features

Restored normal HuggingFace inference behavior

Full Release Notes

Hotfix for a regression in 0.4.3 where generation and transcription could fail outright with "offline mode is enabled" even when the user was online.

### Reliability

- **Inference no longer fails with "offline mode is enabled" while online** ([#524](https://github.com/jamiepine/voicebox/pull/524), reverts the inference-path guards from [#503](https://github.com/jamiepine/voicebox/pull/503)). 0.4.3 wrapped every inference body (`generate`, `transcribe`, `create_voice_clone_prompt`) with a process-wide `HF_HUB_OFFLINE` flip to stop lazy HuggingFace lookups from hanging when the network drops mid-inference ([#462](https://github.com/jamiepine/voicebox/issues/462)). That flag also blocks legitimate metadata calls (e.g. `HfApi().model_info` for revision resolution) so online users started seeing generation fail outright. Inference now runs with the process's default HF state. Load-time offline guards — which weren't the source of the regression — stay in place.

**Known caveat**: users generating without an internet connection may see brief pauses during inference while HuggingFace metadata lookups time out (typically ~30s, after which the library recovers). A proper offline-mode toggle is planned for 0.4.5.