video-01 runs through Replicate; Sora 2 and Veo 3.1 route through the VideoAgent SDK. A model whose key is missing appears disabled with a (key needed) suffix.
Quick Start
1
Add a provider key
Add one key to the
.env file inside the app’s data folder:2
Pick a model and generate
Open the Video tab, pick a model, type a prompt, click Generate. Only models with a configured key are selectable.
3
Watch the result
The MP4 is saved under
media-output/videos/ in the data folder and plays inline in the app.Which model to pick
Pick the model that matches the key you have.Model catalog
Four models ship in the picker. Each unlocks when one of its env keys is set.How generation flows
The SDK path (Sora, Veo) returns MP4 bytes and previews them inline via a data URL. The Replicate path returns a hostedurl instead of a data_url.
Where the file goes
Each generation writes one MP4 tomedia-output/videos/vid_<epoch>_<8hex>.mp4 inside the data folder — for example ~/Library/Application Support/PraisonAI/media-output/videos/vid_1727000000_a1b2c3d4.mp4 on macOS. SDK providers return no hosted URL, so the saved file is the only artifact.
API surface
The tab calls three engine routes on127.0.0.1. Full route reference: Engine API.
GET /media/video/models — the catalog with a per-model configured flag:
POST /media/video — synchronous; returns the finished result. The model field defaults to replicate/minimax/video-01.
GET /media/capabilities — includes the video_models list and a video_hint:
Troubleshooting
The dropdown says (key needed)
The dropdown says (key needed)
The env var isn’t reaching the engine. Add the model’s key to the
.env file in the data folder, then relaunch. See Environment Variables for how the engine picks up keys.praisonaiagents with litellm is required for this provider
praisonaiagents with litellm is required for this provider
Sora and Veo route through
VideoAgent, which needs the llm extra. This is the same lean-environment constraint that Desktop App install describes for slashed chat model ids. Install the extra into the desktop venv:Video generation did not complete (status: failed)
Video generation did not complete (status: failed)
The provider failed to finish the job. No file is written. Retry, or switch to another model.
Related
Video (SDK)
The
VideoAgent and its seconds / size controlsEngine API
The
/media/* routes in full