Claude visitors: new accounts receive $1.00 in bonus API credit within 30 days. One per person; usage credits only.
Use Veo 3 in WorkBuddy.
Veo 3 is Google DeepMind's video generation model that produces 1080p clips up to 8 seconds with native audio — synchronized dialogue, ambient sound, and music generated alongside the video. WorkBuddy speaks MCP natively, so once RunAPI is added as an MCP server, the workbench agent can call Veo 3 as a tool with no plugins to install.
Use the runapi MCP server to generate a cinematic video clip with Google Veo 3.
Requirements:
- Use model "veo-3.1".
- Write a descriptive prompt including scene, camera movement, and audio cues
(dialogue in quotes, ambient sound, music).
- Set duration_seconds to 8 and aspect_ratio to "16:9".
- The task is async. Wait for it to complete, then report the video URL,
the final status, and the cost.
{
"mcpServers": {
"runapi": {
"url": "https://runapi.ai/mcp",
"transport": "streamable_http",
"headers": {
"Authorization": "Bearer $RUNAPI_API_KEY"
}
}
}
}
{
"task_id": "tsk_abc123",
"status": "completed",
"model": "veo-3.1",
"output": {
"video_url": "https://media.runapi.ai/tasks/tsk_abc123/output.mp4",
"duration_seconds": 8,
"resolution": "1080p"
}
}
Use Veo 3 in WorkBuddy in three steps
Add RunAPI as an MCP server
Register an MCP server named runapi in WorkBuddy pointing at https://runapi.ai/mcp over streamable HTTP, with the Authorization header reading your key from RUNAPI_API_KEY. If RunAPI is already connected for other models, Veo 3 is already available as a tool — nothing extra to install.
url: https://runapi.ai/mcp
transport: streamable_http
auth: Bearer $RUNAPI_API_KEY
Prompt the workbench agent
Ask WorkBuddy to generate a video with Veo 3. Describe the scene, camera movement, and audio cues — dialogue in quotes, ambient sound, music. Specify model veo-3.1, duration_seconds of 4, 6, or 8, and an aspect_ratio of 16:9 or 9:16.
Use the runapi MCP server to generate an 8-second Veo 3 clip: ...
Let the agent run the tool and collect the result
WorkBuddy calls the Veo 3 text_to_video tool through the runapi MCP server. The task is async — the agent polls it until the status is completed, then hands back the video URL. The clip includes synchronized audio generated from your prompt.
runapi.text_to_video -> task_id: tsk_abc123 -> status: completed
Veo 3 text_to_video parameters
| Parameter | Type | Description |
|---|---|---|
model |
string |
Required. veo-3.1 (standard quality) or veo-3.1-fast (lower cost, faster generation). |
prompt |
string |
Required. Scene description including visual action, camera movement, and audio cues for dialogue or ambient sound. |
duration_seconds |
integer |
Optional. Video length in seconds. Accepted values: 4, 6, 8. Defaults to 8. |
aspect_ratio |
string |
Optional. Output aspect ratio. Accepted values: 16:9, 9:16, auto. |
input_mode |
string |
Optional. Generation mode. text (default), first_and_last_frames (keyframe-guided), or reference (style reference). |
first_frame_image_url |
string |
Optional. URL of the first frame image. Used when input_mode is first_and_last_frames. |
What is Veo 3 on WorkBuddy?
Veo 3 is Google DeepMind's video model that produces lifelike, cinematic visuals with spot-on ambient audio built in. It generates 1080p clips up to 8 seconds with synchronized dialogue, sound effects, and music — no separate audio pipeline needed. WorkBuddy reaches it through the runapi MCP server, so the workbench agent calls Veo 3 as a standard tool using the single key in RUNAPI_API_KEY.
Veo 3 use cases
Street interview and talking scenes
Ask WorkBuddy for short video scenes with characters speaking dialogue. Describe the conversation in your prompt and Veo 3 produces synchronized lip movement and ambient city noise together.
Atmospheric and landscape content
Create travel vlogging scenes, rain-soaked urban environments, or foggy nature shots where Veo 3's ambient sound generation adds depth without post-production audio work.
Product demo videos with voiceover
Generate product showcase clips where a narrator describes features. Include the voiceover text in your prompt and Veo 3 renders both the visual demo and spoken audio in one pass.
Veo 3 + WorkBuddy questions
Yes. WorkBuddy speaks MCP natively. Add RunAPI as an MCP server with your RUNAPI_API_KEY and the workbench agent can call the Veo 3 text_to_video tool directly — no plugins, bridges, or Google Cloud accounts required.
Veo 3 is a paid model on RunAPI. Each generation is billed per task based on duration and quality tier. veo-3.1-fast costs less than veo-3.1. Check the RunAPI pricing page for current rates. No subscription required — you pay per generation.
Veo 3 generates both video and synchronized audio in a single pass, which takes more processing time. Generation typically takes 60 to 180 seconds. The WorkBuddy agent handles the waiting — it polls the async task and reports back when the video is ready. Use veo-3.1-fast for quicker drafts.
Yes. RunAPI exposes extend_video and upscale_video tools for Veo 3 through the same MCP server. Ask WorkBuddy to extend the clip or upscale it to 1080p or 4K, referencing the task_id from the original generation. Both are async and billed separately.
Veo 3 generates clips of 4, 6, or 8 seconds at up to 1080p base resolution. You can upscale completed videos to 4K using the upscale_video tool. Aspect ratio options are 16:9, 9:16, and auto.
WorkBuddy general setup
Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy.
WorkBuddy setup guide →Try Veo 3 in WorkBuddy today.
Get a free RunAPI key, add the MCP server to WorkBuddy, and generate cinematic video with native audio using Google Veo 3.