Changelog

Restyle an existing video from a text prompt with POST /v1/workflows/video-to-video. Pass an uploaded video or a public link, and the output keeps the original’s length, timing, and cuts. The workflow is available to every account in the SDKs, CLI, MCP, the Zapier, Make, n8n, and Pipedream apps, OpenClaw, and the Python agent framework packages. This release also ends export polling cleanly when a finished export’s file is gone, and checks the full cost of large remix batches before they start.

The Entities API has three new entity types. Use LOCATION for a place or set you want to keep consistent across scenes, PROP for a background object that is not something you sell, and BRAND to hold a logo, a style guide image, and a writing style. Keep using PRODUCT for anything you sell or promote.

GET /v1/projects now returns every project on the team, including projects created in the dashboard. Projects and files you create through the API always show up in the VideoGen app. includeUiProjects and hideFromUi are deprecated and ignored, so existing requests keep working.

Storyboard-to-video scenes can now run up to 30 seconds at every quality, up from 20, including scenes with spoken lines.

Remix actions now run one at a time in the order you list them, whether you send them on a workflow start (remixActions) or through POST /v1/projects/{projectId}/remix. Each action applies to the project as the previous action left it.

Workflow start requests can now render an MP4 before the run is marked succeeded. Set autoExport: true (REST and SDK default is still false). MCP workflow tools default autoExport to true. Zapier, Make, n8n, and Pipedream always auto-export (the field is not shown) and wait until the MP4 is ready. When auto-export is on, wait until status is succeeded and use downloadUrl. Remix actions on the same start request finish before that export.

The no-code apps now start a VideoGen workflow and wait until the exported MP4 is ready. The only instant trigger is project_export.succeeded. Individual media tools, file upload, project lookup, and other webhook triggers are no longer in those apps. Use the REST API or SDKs for that.

Docs no longer advertise unpublished per-framework agent packages. Give an agent VideoGen with the MCP server, or bind the TypeScript or Python SDK in your framework.

Workflow start requests can now render an MP4 before the run is marked succeeded. Set autoExport: true (REST default is still false; MCP and Zapier / Make / n8n / Pipedream default true). When it is on, wait until status is succeeded and use downloadUrl. Remix actions on the same start request finish before that export.

Omitting durationSeconds on POST /v1/tools/generate-video-clip (or passing null) now estimates clip length at generate time so spoken text or the visual beat fits. Previously a missing duration was treated as 6 seconds, which rejected spoken clips longer than 6 seconds. Pass a whole number from 1 to 30 to pin an exact length.

Workflow start requests already accepted hideFromUi to keep generated files off the Media page. The same field now also hides the project from Home and Projects unless the viewer turns on Show hidden projects. Direct project URLs and API get/list still work. Defaults to false.

You can subscribe to project export completion instead of polling the export GET. Every voiceId field also accepts a catalog displayName (for example Matilda or Charlie) in addition to a vg_voic_… id from GET /v1/resources/tts-voices. Existing clients that send ids keep working.

Signed file download and thumbnail URLs in API responses now use VideoGen hosts. uploadUrl for PUT uploads is unchanged.

Version 2.1 of the TypeScript SDK, Python SDK, CLI, MCP server, and OpenClaw plugin. List VideoGen’s built-in catalog on the Entities API, generate spoken lip-synced clips, theme slideshow-to-video decks, and install the OpenClaw plugin from npm or ClawHub.

Slideshow-to-video no longer requires a theme when you are converting an uploaded PDF or PowerPoint’s original pages.

Slideshow-to-video now requires a slideshow theme so every generated slide shares one design system.

POST /v1/tools/generate-image now accepts optional actor, product, and visual-style entity ids. The model uses them as identity/reference the same way in-app image generation does.

POST /v1/tools/generate-video-clip now accepts spokenDialogue (the exact line the subject should speak as native, lip-synced speech) and voiceDescription (how that voice should sound). The model synthesizes the voice from that text. audioFileIds still accepts a reference recording for lip-sync from that file. You can pass spoken text, reference audio, or both.

POST /v1/tools/generate-video-clip now accepts suppressBackgroundMusic. When true, the generated clip will not include a musical soundtrack. Spoken dialogue and environmental sound are still allowed. Use this when you will add background music separately, for example at the project level.

You can now apply a Ken Burns zoom to every still image in a project with a remix action.

Avatar generation now uses reusable ACTOR entities exclusively.