MxChat Video Generation

AI video generation built into your WordPress dashboard, powered by Google Veo, OpenAI Sora, and xAI Grok Imagine. Type a prompt, pick a model, get a finished MP4 — with native audio, multiple aspect ratios, and a Studio Mode that turns one concept into a multi-scene commercial with consistent characters.

Overview

Most AI video tools live in a separate SaaS dashboard, behind a separate login, with their own media library. MxChat Video Generation puts the whole workflow inside wp-admin and saves every output straight to your WordPress media library — ready to embed, schedule, or hand to a client.

You get three best-in-class providers in one plugin: Veo 3.1 / Veo 3.1 Fast / Veo 3 / Veo 3 Fast / Veo 2 from Google, Sora 2 / Sora 2 Pro from OpenAI, and Grok Imagine Video from xAI. Pick the right model per project — fast iteration on Sora 2 or Veo Fast, production fidelity on Sora 2 Pro or Veo 3.1, flexible 1–15 second durations on Grok. Studio Mode stretches a single concept like "3 sports cars drift racing through Tokyo at night" into a fully storyboarded 3–10 scene video with reference-image-locked character consistency and one-click stitching at the end. Requires MxChat (mxchat-basic) with a Pro license active.

Setup

1. Install the plugin via WordPress admin (Plugins → Add New → Upload Plugin) or upload the ZIP.
2. Activate via Plugins → Installed Plugins. The plugin requires MxChat (mxchat-basic) and an active MxChat Pro license — you'll see admin notices if either is missing.
3. Get API keys for the providers you want to use:
- Google Gemini API key (for Veo models) from Google AI Studio. Studio Mode also uses this key for script + reference-image generation.
- OpenAI API key (for Sora 2 / Sora 2 Pro) from your OpenAI account.
- xAI API key (for Grok Imagine and Studio Mode video generation) from x.ai.
4. Navigate to MxChat → Video Generation in the WordPress admin sidebar (or Settings → Video Generation in network admin on multisite).
5. Open Settings, paste your keys, enable video generation, and test with a simple prompt like "A French bulldog running through a field of flowers."

Settings

Enable Video Generation

Master toggle. Off by default. Must be on before any of the Generate, History, or Studio screens will run a job.

Model Selection

Pick the active video model. Options grouped by provider: Veo 3.1 / Veo 3.1 Fast (preview, audio + reference images + extension), Veo 3 / Veo 3 Fast (stable, native audio), Veo 2 (silent, stable), Sora 2 / Sora 2 Pro (fast vs. production tier), Grok Imagine Video (flexible duration). Default is veo-2.

Aspect Ratio

Per-generation control. Veo and Sora support 16:9 widescreen and 9:16 portrait. Grok Imagine adds 4:3, 3:4, 1:1, 3:2, and 2:3 — seven total. The picker only shows ratios valid for the current model.

Resolution

720p on all models. 1080p available on Veo 3.x only. Defaults to 720p for safety.

Duration

Veo 3.x: 4, 6, or 8 seconds. Veo 2: 5, 6, or 8 seconds. Sora 2 / Sora 2 Pro: 4, 8, or 12 seconds. Grok Imagine: any integer from 1 to 15 seconds.

Audio Toggle

On by default for models that support it (Veo 3.x, Sora 2, Sora 2 Pro, Grok Imagine). Veo 2 is silent only — toggle is hidden.

Reference Images

Optional. Upload one starting-frame image for most models, or up to three reference images on Veo 3.1 for character/style guidance throughout the clip.

Negative Prompts

Veo-only field for telling the model what to avoid (e.g. "no text overlays, no watermarks").

Studio Mode Controls

Studio's setup form configures the whole run before any generation kicks off: number of scenes (3–10), aspect ratio, per-scene duration (4–8 seconds), and number of characters to extract from the concept. Once the script is generated, individual character references, scene images, and scene videos each have their own regenerate button with an append-or-replace instruction box.

Features

Three best-in-class video providers in one plugin: Google Veo (3.1, 3.1 Fast, 3, 3 Fast, 2), OpenAI Sora 2 + Sora 2 Pro, and xAI Grok Imagine — all behind one unified interface so you pick the right model per project without juggling tabs.
Native audio generation: Veo 3.x, Sora, and Grok Imagine all bake dialogue and sound effects into the clip during generation. No separate soundtrack step, no muxing.
Studio Mode: A six-step AI workflow that turns a single concept prompt into a multi-scene commercial of 3–10 scenes with character + object consistency across every shot, ending in a single stitched export.
Reference image support: Upload starting-frame photos to guide video generation, or let Veo 3.1 take up to three reference images for locking character and style across the full clip.
Multiple aspect ratios and resolutions: 16:9, 9:16, 4:3, 3:4, 1:1, 3:2, 2:3 at 720p or 1080p. Durations from 1 to 15 seconds depending on the model.
Auto-save to media library: Every generated video lands in WordPress media management automatically as soon as generation completes — ready to embed in a post, schedule, or hand to a client.
Generation history with real-time status: Track progress with estimated completion times. Regenerate any individual scene or video while others are still processing. Resume Studio projects from any step after closing the browser.
One-click stitching: Combine all Studio Mode scenes into a single downloadable video using server-side FFmpeg if available, or client-side ffmpeg.wasm as a fallback.

API & Integration

The plugin talks to three video generation APIs and one image generation API:

Google Veo API (via Gemini) — handles Veo 3.1, Veo 3.1 Fast, Veo 3, Veo 3 Fast, and Veo 2 generation requests. Same Gemini key also powers Studio Mode's script generation and Gemini Nano Banana reference + scene image generation.
OpenAI Sora API — handles Sora 2 and Sora 2 Pro generation requests using your OpenAI API key.
xAI Grok Imagine API — handles Grok Imagine Video generation (and all Studio Mode video generation) using your xAI API key.

Studio Mode projects persist in a custom table {prefix}mxchat_studio_projects with concept, config, script, reference data, scene images, and video data columns — so projects survive transient cache flushes. Stitching uses server-side FFmpeg when the binary is detected; otherwise the plugin falls back to client-side processing in the browser via WebAssembly.

Requirements

MxChat (mxchat-basic): Required, active.
MxChat Pro License: Required — features are gated behind an active Pro license. See /pricing/.
WordPress: 5.8 or newer.
PHP: 7.4 or newer.
API keys: At minimum one provider key for the model(s) you plan to use. Studio Mode needs both a Google Gemini key (script + images) and an xAI key (video generation).
Server-side stitching (optional): FFmpeg installed on the host. If absent, the plugin falls back to client-side stitching in the browser.

Troubleshooting

"API key not configured" or 401 / 403 errors

The provider key for the selected model is missing or invalid. Check MxChat → Video Generation → Settings and confirm the right key is filled in for the active model's provider. Google keys start with AIza...; OpenAI keys start with sk-.... Verify the key has video generation permissions enabled on the provider's console.

Quota exceeded / rate limit errors

All three providers enforce per-account quotas and concurrency limits — heavy Studio Mode use can hit them fast. Check your provider dashboard for current limits and billing status. If you're running parallel Studio video generation, try lowering the number of scenes or generating in smaller batches.

"Session expired" in Studio Mode

Fixed in 3.0.1 — Studio steps now fall back to the mxchat_studio_projects database table when transient cache entries expire. If you're seeing this on a project created before 3.0.1, reload the project from the Studio screen to trigger the fallback.

Generation hangs or times out

Generation times vary widely by model — anywhere from 8 seconds (Veo Fast) to 6 minutes (Veo 3.1). Server-side timeouts on shared hosts can cut off polling before the video finishes. If a job appears stuck, check the History tab — completed videos often show up there even when the generation panel timed out.

Stitched video fails to download

If server-side FFmpeg isn't installed, stitching runs in the browser via ffmpeg.wasm and can be slow or memory-hungry on long videos. Try downloading scenes individually as a fallback, or install FFmpeg on the host to switch to server-side stitching.

"No videos found" when downloading ZIP from a reloaded project

Fixed in 3.0.1 via the same project-based fallback that resolved Studio session expiry. Upgrade to 3.0.1 or newer.

Last reviewed by Sage on 2026-05-21. Spotted an issue? Open a ticket and we'll patch the doc.