Arion Release Notes

All released versions, newest first.

Download the latest Arion installer →

Arion 1.0.1 — May 1, 2026 · Maintenance release

A focused maintenance release driven by a structured QA pass against 1.0.0. Every change in this release is a real customer-visible bug fix or UX improvement — no new features, no breaking changes for existing customers.

Bug fixes

UX improvements

Installation prerequisites

Tier 3 (Local AI) requires the Microsoft Visual C++ 2015-2022 Redistributable (x64). Most modern Windows machines already have it installed; if Settings → System Status reports a bundled-but-failed-to-load library, install vc_redist.x64.exe from Microsoft and restart Arion. CPUs from before roughly 2013 may also lack the AVX2 instructions required by the Tier 3 components.

Notable change for Family Edition

Video and audio transcription is temporarily unavailable. Arion 1.0.1 ships without the speech-to-text engine. The standard build no longer bundles faster-whisper and its native dependencies. An on-demand installer for the transcription engine — shared with Cadenzium and downloaded once per machine — is planned for 1.0.2. Until then, video (.mp4, .mkv, etc.) and audio (.mp3, .wav, etc.) files are skipped during scans on Family Edition. Settings → Video & Audio shows an explanatory note when the engine isn't installed.

Planned for 1.0.2

· On-demand transcription engine installer — opt-in download of the faster-whisper engine and its dependencies, restoring video and audio indexing for Family Edition. Shared with Cadenzium, so customers who own both products download the engine once.

· Tier 3 integration test pass — an automated smoke-test harness for the local AI path so silent failures (missing native modules, embedding-model configuration mismatches) get caught before release rather than during launch testing.

Arion 1.0.0 — April 29, 2026 · Initial release

Arion 1.0.0 is the first public release. It indexes documents on your machine (and optionally your cloud storage) and gives you fast full-text search with optional AI question-answering — all under a clear single-tenant model where your data stays on hardware you control.

Editions

Search

File formats

Family+ features

Archive features

Platform and install

Planned for upcoming versions

These capabilities are on the post-1.0 roadmap and not in this release:

· OCR for image-only PDFs — a scanned receipt or photo-of-a-document is currently indexed by filename only. OCR support is the highest-impact feature gap and is being prioritized.

· Azure-side audio/video transcription (Tier 2) — currently transcription runs locally with faster-whisper regardless of search tier. An Azure Speech provider option is planned for customers who prefer cloud-side STT.

· Azure-side image description (Tier 2) — Archive's image description currently requires a local Ollama vision model. An Azure AI Vision option is planned for customers without a local GPU.

· Multi-provider cloud AI — beyond Azure OpenAI, support for OpenAI-compatible endpoints (Gemini, OpenRouter, and others).