Can I use Seedance in WorkBuddy?

Yes. WorkBuddy speaks MCP natively. Add RunAPI as an MCP server with your RUNAPI_API_KEY and the workbench agent can call the Seedance text_to_video tool with model set to seedance-2.0. The same server covers chat, image, and every other video model.

How does Seedance per-second billing work?

You are billed based on the actual duration of the generated video and the output resolution you select. A 480p video costs less per second than 1080p. The cost is deducted after the video completes, not when the task is created.

Can I use English prompts for non-Chinese content on Seedance?

Yes. Seedance accepts English prompts and generates multi-language content. It supports both English and Chinese prompt input regardless of the target video content language.

Can Seedance generate video from an image?

Yes. Give WorkBuddy an image URL to use as the first frame along with a text prompt. Seedance uses the image as the opening frame and generates motion from there. You can also set a last frame image to constrain the ending.

How do reference audio URLs work with Seedance?

Seedance 2.0 can sync generated video motion to an audio track. Pass the audio file URL in reference_audio_urls and the model aligns visual motion to the audio — useful for music videos or dialogue-driven scenes without a separate audio-to-video step.

Claude visitors: new accounts receive $1.00 in bonus API credit within 30 days. One per person; usage credits only.

WORKBUDDY + SEEDANCE

Use Seedance in WorkBuddy.

Seedance 2.0 generates 4–15 second videos at up to 1080p with per-second billing starting around $0.05/sec — the lowest per-second cost among RunAPI video models. It supports multimodal reference inputs (images, video, and audio URLs), first/last frame control, and native audio sync. WorkBuddy calls it as an MCP tool through the same runapi server used for every other model.

Get API Key Read the docs

one MCP server · text to video tool · per-second billing

Use the runapi MCP server to generate a product showcase video with
Seedance 2.0.

Requirements:
- Use model "seedance-2.0".
- Prompt: a ceramic coffee mug rotates slowly on a wooden table, steam
  rising, warm morning light from a window, cinematic.
- Set duration_seconds to 8, aspect_ratio to "16:9", and
  output_resolution to "1080p".
- The task is async. Wait for it to complete, then report the video URL
  and the per-second cost.

{
  "mcpServers": {
    "runapi": {
      "url": "https://runapi.ai/mcp",
      "transport": "streamable_http",
      "headers": {
        "Authorization": "Bearer $RUNAPI_API_KEY"
      }
    }
  }
}

{
  "task_id": "tsk_abc123",
  "status": "completed",
  "model": "seedance-2.0",
  "output": {
    "video_url": "https://media.runapi.ai/tasks/tsk_abc123/output.mp4",
    "duration_seconds": 8,
    "resolution": "1080p"
  }
}

Copy the prompt into WorkBuddy seedance

HOW IT WORKS

Use Seedance 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. Seedance shows up as a callable tool alongside the rest of the RunAPI catalog.

url: https://runapi.ai/mcp
transport: streamable_http
auth: Bearer $RUNAPI_API_KEY

Prompt the workbench agent

Ask WorkBuddy to generate a video with Seedance 2.0. Include a prompt, duration_seconds (4–15), aspect_ratio, and output_resolution. Optionally attach first frame, reference image, or reference audio URLs for multimodal control.

Use the runapi MCP server to generate an 8-second Seedance 2.0 clip: ...

Let the agent run the tool and collect the result

WorkBuddy calls the Seedance text_to_video tool and receives a task_id immediately. The agent polls the async task until it completes, then reports the output video URL. Billing is per-second based on the generated duration and resolution.

runapi.text_to_video -> task_id: tsk_abc123 -> status: completed

PARAMETERS

Seedance API parameters

Parameter	Type	Description
`model`	`string`	Required. seedance-2.0, seedance-2.0-fast, seedance-1.5-pro, seedance-v1-pro.
`prompt`	`string`	Required. Text description of the video scene to generate.
`duration_seconds`	`integer`	Video length in seconds. 4–15 for Seedance 2.0, 5 or 10 for v1 variants.
`aspect_ratio`	`string`	Output aspect ratio. Accepted: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9, auto.
`output_resolution`	`string`	Video resolution. Accepted: 480p, 720p, 1080p. Higher resolution costs more per second.
`reference_audio_urls`	`array`	Optional. URLs of reference audio files for native audio sync in the generated video.

What is Seedance on WorkBuddy?

Seedance 2.0 by ByteDance is a leaderboard-topping video model with native audio integration and tight audio-video sync. It generates 4 to 15 second clips at up to 1080p with multi-shot storytelling, director-level control over scene transitions, and actual lip-sync that works. WorkBuddy calls it as an MCP tool through the runapi server, and RunAPI bills per second of generated video.

Seedance use cases

Dialogue-heavy shorts

Ask WorkBuddy for short clips with characters speaking — Seedance handles lip sync and dialogue attribution across multiple speakers, making it a fit for conversational content and talking-head scenes.

Short-form content for TikTok and Reels

Produce platform-ready vertical video at exact durations. Per-second billing means a 5-second clip costs a third of a 15-second one.

Product demonstration prototypes

Create product demo clips with audio narration synced to visual action. Attach a reference audio URL to align the video motion to a voiceover track.

FAQ

Seedance + WorkBuddy questions

WorkBuddy general setup

Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy.

WorkBuddy setup guide →

Seedance model catalog

See all Seedance variants, pricing tiers, and API docs.

Seedance on RunAPI →

Try Seedance in WorkBuddy today.

Get a free RunAPI key, add the MCP server to WorkBuddy, and generate per-second-billed video with Seedance 2.0.

Browse models →