Claude visitors: new accounts receive $1.00 in bonus API credit within 30 days. One per person; usage credits only.
Use Wan in WorkBuddy.
Wan is Alibaba's open-source video and image generation model, Apache 2.0 licensed and ranked #1 on the Artificial Analysis text-to-video leaderboard. It spans 20+ variants from Wan 2.2 through 2.7 — text-to-video, image-to-video, speech-to-video with lip-sync, video editing via R2V, and image generation up to 4K. Add RunAPI as an MCP server once and every Wan endpoint becomes a callable tool inside the WorkBuddy workbench.
Generate a video with Alibaba Wan 2.7 using the runapi MCP server.
Requirements:
- Use the RunAPI MCP tool for text-to-video generation.
- Set model to "wan-2.7-text-to-video".
- Set output_resolution to "1080p" for full HD output.
- Prompt: "A drone shot rising over terraced rice paddies at golden hour, mist rolling through the valleys, slow upward camera tilt".
- The task is async — wait for the tool to report the task as completed, then give me the video URL.
{
"mcp_servers": {
"runapi": {
"url": "https://runapi.ai/mcp",
"transport": "streamable_http",
"headers": {
"Authorization": "Bearer $RUNAPI_API_KEY"
}
}
}
}
{
"task_id": "tsk_abc123",
"status": "completed",
"model": "wan-2.7-text-to-video",
"output": {
"video_url": "https://media.runapi.ai/outputs/tsk_abc123.mp4"
}
}
Use Wan in WorkBuddy in three steps
Add the RunAPI MCP server
Register an MCP server named runapi in WorkBuddy pointing at https://runapi.ai/mcp over streamable HTTP, with your key read from the RUNAPI_API_KEY environment variable. If RunAPI is already connected for chat or images, the same server covers all 20+ Wan variants — no extra setup.
export RUNAPI_API_KEY=runapi_xxx
# MCP server: runapi → https://runapi.ai/mcp
Prompt the workbench agent
Tell WorkBuddy what to generate and which Wan variant to use — wan-2.7-text-to-video for text-to-video, wan-2.7-image-to-video with a first_frame_image_url for image-to-video, or wan-2.2-a14b-speech-to-video-turbo with source_audio_url and source_image_url for lip-synced speech video. The agent picks the matching RunAPI MCP tool and fills in the parameters.
"Generate a 1080p video with wan-2.7-text-to-video: ..."
Let the tool return the result
The RunAPI MCP tool creates the task, handles the async polling until the status is completed, and hands the finished video or image URL back into the workbench — no manual status checks needed.
status: completed → video_url
Wan text_to_video parameters
| Parameter | Type | Description |
|---|---|---|
model |
string |
Required. wan-2.7-text-to-video, wan-2.6-text-to-video, wan-2.5-text-to-video, wan-2.2-a14b-text-to-video-turbo, or wan-2.7-r2v. |
prompt |
string |
Required. Text description of the desired video scene, including camera motion, lighting, and subject detail. |
output_resolution |
string |
Optional. 720p or 1080p for Wan 2.5+. Wan 2.2 also accepts 480p and 580p. Defaults to 720p. |
aspect_ratio |
string |
Optional. For wan-2.7-r2v only. Accepted values: 16:9, 9:16, 1:1, 4:3, 3:4. |
duration_seconds |
integer |
Optional. For wan-2.7-r2v only. Video length in seconds, 2 to 10. |
seed |
integer |
Optional. Reproducibility seed for deterministic output. |
What is Wan on WorkBuddy?
Wan by Alibaba is an open-source (Apache 2.0) video model ranked at the top of the Artificial Analysis text-to-video leaderboard. It offers first-frame and last-frame control for endpoint-anchored generation, multi-shot video with character consistency, and native audio including lip-synced speech-to-video. Through the runapi MCP server, WorkBuddy reaches all 20+ Wan variants as callable tools with a single RUNAPI_API_KEY.
Wan use cases
Storyboard-to-video workflow
Use first-frame and last-frame anchoring to turn storyboard panels into video sequences. Each clip starts and ends on your keyframes, maintaining visual continuity across a multi-shot project.
Virtual presenters and brand mascots
Generate talking-head video from a face image and audio file using Wan's speech-to-video tool. The model handles lip sync and head movement for consistent brand spokesperson content.
Multi-shot sequences with character consistency
Build dialogue-heavy or narrative content where the same character appears across multiple clips. Wan's temporal consistency keeps faces and outfits stable between shots.
Wan + WorkBuddy questions
All of them. text_to_video, image_to_video, speech_to_video, text_to_image (Wan 2.7 Image), edit_video, and animate. The runapi MCP server exposes each as a tool — for example wan-2.7-text-to-video for video generation and wan-2.7-image for image generation up to 4K.
Add RunAPI as an MCP server named runapi pointing at https://runapi.ai/mcp, with your key in the RUNAPI_API_KEY environment variable. Once connected, ask WorkBuddy to list the server's tools and every Wan variant — plus the rest of the RunAPI catalog — is ready to call.
Wan 2.5 introduced 1080p output. Wan 2.6 added video editing (R2V) and flash variants for faster generation. Wan 2.7 adds image generation (wan-2.7-image, wan-2.7-image-pro up to 4K), video editing (wan-2.7-edit-video), and improved text-to-video quality that leads the Artificial Analysis leaderboard.
Ask the workbench agent to use wan-2.2-a14b-speech-to-video-turbo with source_audio_url (the audio file) and source_image_url (the face to animate). Wan generates a lip-synced video where the face speaks the audio. Output resolution supports 480p, 580p, or 720p.
Yes. Wan is released under Apache 2.0 by Alibaba and the model weights are publicly available. Through RunAPI you skip the GPU setup — WorkBuddy calls one MCP tool and gets the video or image back. If you need a self-hosted pipeline for privacy, the same weights run on your own infrastructure.
WorkBuddy general setup
Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy.
WorkBuddy setup guide →Try Wan in WorkBuddy today.
Get a free RunAPI key, add the MCP server to WorkBuddy, and generate video with the #1 ranked open-source model — text-to-video, image-to-video, or speech-to-video.