--- title: Use Seedance in WorkBuddy via RunAPI — MCP Guide | RunAPI description: Generate videos with Seedance 2.0 in WorkBuddy over MCP. Per-second billing, multimodal references, and native audio through one RunAPI MCP server. url: https://runapi.ai/workbuddy-seedance.md canonical: https://runapi.ai/workbuddy-seedance locale: en site: RunAPI image: https://runapi.ai/assets/opengraph-bfaaa0f0.png alternates: en: https://runapi.ai/workbuddy-seedance zh-CN: https://runapi.ai/zh-CN/workbuddy-seedance es: https://runapi.ai/es/workbuddy-seedance ja: https://runapi.ai/ja/workbuddy-seedance de: https://runapi.ai/de/workbuddy-seedance fr: https://runapi.ai/fr/workbuddy-seedance pt-BR: https://runapi.ai/pt-BR/workbuddy-seedance ko: https://runapi.ai/ko/workbuddy-seedance it: https://runapi.ai/it/workbuddy-seedance nl: https://runapi.ai/nl/workbuddy-seedance pl: https://runapi.ai/pl/workbuddy-seedance tr: https://runapi.ai/tr/workbuddy-seedance zh-TW: https://runapi.ai/zh-TW/workbuddy-seedance zh-HK: https://runapi.ai/zh-HK/workbuddy-seedance ar: https://runapi.ai/ar/workbuddy-seedance x-default: https://runapi.ai/workbuddy-seedance model: seedance --- > HTML version: https://runapi.ai/workbuddy-seedance > Site index for agents: https://runapi.ai/llms.txt # 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](https://runapi.ai/login) - [Read the docs](https://runapi.ai/docs/guides) one MCP server · text to video tool · per-second billing ### Prompt ```text 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. ``` ### MCP config ```bash { "mcpServers": { "runapi": { "url": "https://runapi.ai/mcp", "transport": "streamable_http", "headers": { "Authorization": "Bearer $RUNAPI_API_KEY" } } } } ``` ### Result ```json { "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" } } ``` ## Use Seedance in WorkBuddy in three steps 1. **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 ` 2. **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: ...` 3. **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` ## 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. ## Seedance + WorkBuddy questions ### 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. - [WorkBuddy setup guide →](https://runapi.ai/workbuddy.md) - Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy. - [Seedance on RunAPI →](https://runapi.ai/models/seedance.md) - See all Seedance variants, pricing tiers, and API docs. ## 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 →](https://runapi.ai/models.md) --- ## More from RunAPI - [Home](https://runapi.ai/.md) ### Product - [Model Catalog](https://runapi.ai/models.md) - [Pricing](https://runapi.ai/pricing.md) - [Providers](https://runapi.ai/models#all-models) ### Developers - [Documentation](https://runapi.ai/docs/guides) - [SDKs](https://runapi.ai/sdk.md) - [CLI](https://runapi.ai/cli.md) - [MCP Server](https://runapi.ai/mcp.md) - [x402](https://runapi.ai/x402.md) ### Guides - [Claude Code vs Cursor](https://runapi.ai/claude-code-vs-cursor.md) - [Cursor API Setup](https://runapi.ai/cursor-api-setup.md) - [RunAPI vs OpenRouter](https://runapi.ai/openrouter-alternative.md) ### Company - [Enterprise](https://runapi.ai/contact.md) - [Contact](https://runapi.ai/contact.md) ### Legal - [Terms](https://runapi.ai/terms.md) - [Privacy](https://runapi.ai/privacy.md) - [Site index for agents](https://runapi.ai/llms.txt) Contact: contact@runapi.ai ## Structured data ```json [ { "@context": "https://schema.org", "inLanguage": "en", "@type": "WebSite", "name": "RunAPI", "url": "https://runapi.ai/", "potentialAction": { "@type": "SearchAction", "target": { "@type": "EntryPoint", "urlTemplate": "https://runapi.ai/models?q={search_term_string}" }, "query-input": "required name=search_term_string" } }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "Organization", "name": "RunAPI", "url": "https://runapi.ai/", "logo": { "@type": "ImageObject", "url": "https://runapi.ai/icon.svg" }, "sameAs": [ "https://github.com/runapi-ai" ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "SoftwareApplication", "name": "RunAPI Seedance for WorkBuddy", "applicationCategory": "DeveloperApplication", "description": "Generate videos with Seedance 2.0 in WorkBuddy over MCP. Per-second billing, multimodal references, and native audio through one RunAPI MCP server.", "url": "https://runapi.ai/workbuddy-seedance" }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "FAQPage", "mainEntity": [ { "@type": "Question", "name": "Can I use Seedance in WorkBuddy?", "acceptedAnswer": { "@type": "Answer", "text": "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." } }, { "@type": "Question", "name": "How does Seedance per-second billing work?", "acceptedAnswer": { "@type": "Answer", "text": "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." } }, { "@type": "Question", "name": "Can I use English prompts for non-Chinese content on Seedance?", "acceptedAnswer": { "@type": "Answer", "text": "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." } }, { "@type": "Question", "name": "Can Seedance generate video from an image?", "acceptedAnswer": { "@type": "Answer", "text": "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." } }, { "@type": "Question", "name": "How do reference audio URLs work with Seedance?", "acceptedAnswer": { "@type": "Answer", "text": "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." } } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "HowTo", "name": "How to use Seedance in WorkBuddy via RunAPI", "description": "Add RunAPI as an MCP server in WorkBuddy, prompt the workbench agent, and let it call the Seedance text_to_video tool with per-second billing.", "step": [ { "@type": "HowToStep", "position": 1, "name": "Add RunAPI as an MCP server", "text": "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/workbuddy-seedance#how-step-1" }, { "@type": "HowToStep", "position": 2, "name": "Prompt the workbench agent", "text": "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.", "url": "https://runapi.ai/workbuddy-seedance#how-step-2" }, { "@type": "HowToStep", "position": 3, "name": "Let the agent run the tool and collect the result", "text": "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.", "url": "https://runapi.ai/workbuddy-seedance#how-step-3" } ] }, { "@context": "https://schema.org", "inLanguage": "en", "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://runapi.ai/" }, { "@type": "ListItem", "position": 2, "name": "RunAPI Seedance for WorkBuddy", "item": "https://runapi.ai/workbuddy-seedance" } ] } ] ```