2.5.3 v1.3.5
tobychui/zoraxyAug 22, 2026 → Aug 22, 20260 days between releases
What's New
Expanded AI ecosystem with new providers, security hardening, and WebUI settings
New Features
- Added MiniMax and Fish Audio text-to-speech support
- Added Anthropic Claude as a native LLM provider
- Added Shengsuan AI and WaveSpeed text-to-video material sources
- Introduced reusable WebUI generation settings with preset import/export
- Added LLM-generated social captions for all supported cross-post platforms
Improvements
- Enhanced security with optional API key authentication and stricter file path validation
- Added actionable startup error when FFmpeg is unavailable
- Fixed Docker dependency installation retries
Bug Fixes
- Fixed the last subtitle line being clipped for some text and font combinations
- Fixed Docker dependency installation retries
- Fixed startup error when FFmpeg is unavailable
Upgrade Notes
Existing installations remain backward compatible with default settings. You may optionally configure app.api_key for enhanced security. Review custom audio input paths to ensure they comply with new restrictions.
The Two Releases
2.5.3
Aug 22, 2026· 2 months ago
Minimal release notes: "### 🐞 Bug Fixes - #7754 fix: release with wrong version number Read more in 2.5.1 changelog: https://github.com/lo"
Full release notesv1.3.5
Aug 22, 2026· 2 months ago
This release significantly expands the AI provider ecosystem by adding MiniMax, Fish Audio, Anthropic Claude, and new video sources, while introducing reusable WebUI settings and robust security measures like API key authentication.
Full release notes