Skip to main content

New AI models, faster onboarding, and a smarter video editor

· 2 min read

AIExpedite added Meta and Muse model support, faster computer onboarding, real-time iOS voice chat, and a video editor assistant that can edit storyboards directly, alongside workspace, deployment, and reliability fixes.

This batch covers a lot of ground: new AI model options, a smoother onboarding path for new computers, real-time voice on iOS, and a more capable video editor assistant. There are also a handful of reliability fixes to usage tracking, deployments, and workspace management.

New AI models​

  • Meta and Muse models are now available across chat, video generation, and cost tracking, with correct API keys and provider branding throughout.

Faster onboarding​

  • Newly paired computers, including on Windows, now start automatic onboarding right away instead of waiting on a token refresh.

Workspace management​

  • Fixed a bug where editing your profile could rename a shared workspace instead of your personal one, and new invitees now land directly in the workspace they were invited to.
  • Removing a member now asks for confirmation first and sends the removed member a notification email.

Calendar​

  • You can now view and edit event availability (Busy, Free, Tentative) right from the calendar, kept in sync with Google Calendar.

Voice​

  • Real-time, two-way voice chat is now available on iOS, matching the existing web experience.
  • Voice navigation now correctly understands phrases like "take me to the feedback page."

Video editor​

  • The AI chat assistant can now read and directly edit your open video project's storyboard, scenes, and scripts.
  • Fixed scene generation loading and error states, improved the mobile layout, and added options for audio overlap and scene playback alignment.

Deployments​

  • Deploy approvals now use deterministic auto-merge rules instead of prompts, and fully merged deployments finish automatically instead of getting stuck in review.
  • Added merge-conflict resolution settings and clearer deploy card notices when a deployment needs your attention.

Reliability​

  • Fixed stale usage and quota metrics after Antigravity, Codex CLI, and Claude updates, and corrected API key handling for Meta and NeuralEdge models.

Plus 12 smaller improvements not covered here.