Seedance 2.5 重磅上線 限時優惠低至 49 折,最低僅需 0.33元/秒
即刻升級
Back to changelog

MiniMax H3 video, vocal songs, translation review, and Hermes Agent

Generate with two new video models, create vocal songs, review source transcripts before lip sync, and run Hermes inside Desktop.

Web

September 4, 2026

No update required

Desktop

0.3.12

Minimum version

Agent Plugin

0.2.26

Minimum version

Video Gen has first- and last-frame slots, a model selector, settings, and a draft prompt. No generation was submitted.
Video Gen has first- and last-frame slots, a model selector, settings, and a draft prompt. No generation was submitted. 介面示意,並非此歷史版本發布時的原始截圖。 ChatCut Web 截圖日期 英文介面 查看完整尺寸截圖

Feature updates

AI video

Generate video with MiniMax H3 and H3 Max

MiniMax H3 adds text, frames, references, and 2K options; H3 Max provides a higher-quality frame-led path with model-specific input limits.

Version requirement: Desktop 0.3.5 or later

Related docs: AI Video Generation

Review the source transcript before lip-sync translation

Lip-sync video translation now presents an editable source transcript before submission, while audio-only translation can still proceed directly.

Version requirement: Desktop 0.3.4 or later

Music

Generate vocal songs as well as instrumental music

Music requests can create a structured vocal song with lyrics and singing direction, or continue through the existing instrumental path.

Version requirement: Desktop 0.3.8 or later

Agents

Run Hermes Agent inside ChatCut Desktop

Desktop detects Hermes, guides sign-in, configures the current project's MCP connection, and restores the session and selected model after restart.

Version requirement: Desktop 0.3.4 or later

Related docs: ChatCut Desktop

Desktop

Use the editor in Japanese and Traditional Chinese

Web and Desktop add Japanese and Traditional Chinese interface catalogs alongside English, Spanish, and Simplified Chinese.

Version requirement: Desktop 0.3.5 or later