---
title: "RunAPI 経由で Hermes Agent から Seedance を使う — 動画 API ガイド"
url: "https://runapi.ai/ja/hermes-seedance.md"
canonical: "https://runapi.ai/ja/hermes-seedance"
locale: "ja"
model: "seedance"
---

# Hermes Agent で Seedance を使う。

Seedance 2.0 は 4〜15秒・最大 1080p の動画を生成し、秒単位の課金は約 $0.05/秒から——RunAPI の動画モデルの中で秒あたりのコストが最も低いものです。マルチモーダル参照入力（画像、動画、音声 URL）、最初/最後のフレーム制御、ネイティブ音声同期に対応します。Hermes Agent は RunAPI のカスタムエンドポイント経由で呼び出します——custom:runapi を一度設定すれば、同じキーを再利用できます。

## API example

```bash
curl -X POST https://runapi.ai/api/v1/seedance/text_to_video \
  -H "Authorization: Bearer $RUNAPI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0",
    "prompt": "A ceramic coffee mug rotates slowly on a wooden table, steam rising, warm morning light from a window, cinematic",
    "duration_seconds": 8,
    "aspect_ratio": "16:9",
    "output_resolution": "1080p"
  }'

```

### Response

```json
{
  "task_id": "tsk_abc123",
  "status": "pending",
  "model": "seedance-2.0"
}

```

## How it works

1. **Configure RunAPI** — Set RUNAPI_API_KEY in the environment where Hermes Agent runs. If you already added RunAPI as a custom:runapi provider for chat, the same key and base_url handle video generation. If not, add the custom provider with base_url https://runapi.ai/v1 and run hermes doctor.
2. **Call Seedance text_to_video** — Send a POST to the text_to_video endpoint with model set to seedance-2.0. Include a prompt, duration_seconds (4–15), aspect_ratio, and output_resolution. Optionally attach first_frame_image_url, reference_image_urls, or reference_audio_urls for multimodal control. Hermes Agent sends this through the custom:runapi provider.
3. **Poll for the result** — The endpoint returns a task_id immediately. Poll the task status endpoint until the status is completed, then read the output video URL from the response. Billing is per-second based on the generated video duration and resolution.

## Parameters

| Parameter | Type | Description |
|-----------|------|-------------|
| `model` | `string` | Required. seedance-2.0, seedance-2.0-fast, seedance-1.5-pro, seedance-v1-pro, seedance-v1-lite. |
| `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. |
| `first_frame_image_url` | `string` | Optional. URL of an image to use as the first frame. Enables image-to-video workflows. |
| `last_frame_image_url` | `string` | Optional. URL of an image to use as the last frame. Constrains the ending scene. |
| `reference_image_urls` | `array` | Optional. URLs of reference images for pose, depth, or edge guidance. |
| `reference_audio_urls` | `array` | Optional. URLs of reference audio files for native audio sync in the generated video. |
| `reference_video_urls` | `array` | Optional. URLs of reference videos for motion or style transfer. |
| `callback_url` | `string` | Optional. Webhook URL that receives a POST when the task completes. |

## FAQ

### Can I use Seedance in Hermes Agent?

Yes. Configure RunAPI as a custom provider in Hermes Agent with base_url https://runapi.ai/v1, then call the text_to_video endpoint with model set to seedance-2.0. The same API key handles both chat and video generation.

### How does Seedance compare to Sora?

Seedance 2.0 leads several video generation leaderboards and offers native audio sync that many competitors lack. It generates audio and video in a single pass, while most other models require separate audio generation. Per-second billing on RunAPI also makes it more cost-predictable.

### Does Hermes Agent need a plugin for video generation?

No. Hermes Agent sends HTTP requests through the custom:runapi provider the same way it sends chat requests. The text_to_video endpoint accepts a JSON body and returns a task ID. No additional plugins or extensions are required.

### Will Seedance expand beyond 15 seconds per clip?

Currently Seedance 2.0 generates clips between 4 and 15 seconds. For longer content, chain multiple clips using character-consistent prompts and first/last frame anchoring. Hermes Agent can automate this chaining in a multi-step workflow.

### How does Hermes Agent control Seedance video duration?

Set the duration parameter in seconds (4-15) when calling the Seedance endpoint through your Hermes Agent custom:runapi provider. Billing scales linearly with duration, so Hermes Agent can optimize cost by requesting only the length needed.

### Can Hermes Agent batch multiple Seedance generations in parallel?

Yes. Hermes Agent can dispatch multiple Seedance tasks simultaneously through RunAPI, each with different prompts or settings, and collect all results when they complete. This is useful for generating video variations at scale.


## Links

- [Hermes Agent セットアップガイド →](https://runapi.ai/ja/hermes-agent)
- [RunAPI の Seedance →](https://runapi.ai/ja/models/seedance)
- [Model catalog](https://runapi.ai/ja/models)
- [API docs](https://runapi.ai/ja/docs)