Skip to content

Formerly KrillinAI, VideoTranslation and Dubbing Tool for 120+ Languages. Open-source AI workspace for creators, powered by Codex. Video downloader, video translation, create videos, images, audios, and edits with Agents in one place. For your Social Media like YouTube, TikTok, Instagram, etc.

chore(release): prepare v3.2.9

Leggettf7e628a83faa
diff --git a/apps/desktop/package.json b/apps/desktop/package.json
index 476b724f..f594f8f3 100644
--- a/apps/desktop/package.json
+++ b/apps/desktop/package.json
@@ -1,6 +1,6 @@
{
"name": "@opencreator/desktop",
- "version": "3.2.8",
+ "version": "3.2.9",
"private": true,
"description": "OpenCreator 本地 Codex Dashboard",
"author": "OpenCreator",
diff --git a/apps/desktop/release-notes/v3.2.9.md b/apps/desktop/release-notes/v3.2.9.md
new file mode 100644
index 00000000..c718d690
--- /dev/null
+++ b/apps/desktop/release-notes/v3.2.9.md
@@ -0,0 +1,9 @@
+## What's New
+
+- Improved the video translation workflow with clearer stage progress, subtitle editing, live composition previews, and smoother rendering and download steps.
+- Made subtitle translation more resilient with sentence-level checkpoints, recovery of incomplete translations, and improved subtitle timing and line wrapping.
+- Improved translation model selection and added direct HTTP requests for API-key text providers, allowing local subtitle translation without starting a Codex runtime.
+- Improved media downloads with parallel source retrieval and support for resuming interrupted downloads.
+- Refined shared model selectors, model-specific controls, and voice library interactions across Creator workspaces.
+- Updated the default OpenAI image model to gpt-image-2 and migrated saved gpt-image-1 settings while preserving independently configured models.
+- Fixed parallel tool calls from Chat-compatible providers being combined when streamed chunks omit tool indexes.