✨ Node.js Version: This script is implemented using Node.js, no Python environment required. The entry script automatically detects the Node.js runtime (prioritizes system node, falls back to LobsterAI's built-in runtime), making it out-of-the-box for both Windows and Mac users.

• Base URL:

  https://ark.cn-beijing.volces.com/api/v3

• API Key: Read from the environment variable

  ARK_API_KEY

• Authentication:

  Authorization: Bearer {API_KEY}

• SDK: Compatible with Volcano Ark Python SDK

1. Submit Task - Call the API to create a video generation task and obtain the

   task_id

2. Poll Status - Query the task status every few seconds until it changes to

   succeeded

3. Download Video - Download the generated MP4 file from the

   video_url

   field

• 2 million tokens free quota
• No free quota for flex mode (offline inference)

• RPM Limit: Maximum number of tasks allowed to be created per minute for the same model under the account
• Concurrency Limit: Maximum number of tasks being processed at the same time
• TPD Limit: Total token call limit for the same model in flex mode within a day

• Task data (including video URLs) is only retained for 24 hours
• It will be automatically cleared after the timeout
• Be sure to download and save the generated video in a timely manner

bash "$SKILLS_ROOT/seedance/scripts/generate-video.sh" \
  --prompt "A kitten playing on the grass, sunny day, camera slowly zooms in" \
  --duration 5 \
  --output generated_video.mp4

• "Realistic style, under a clear blue sky, a large field of white daisies, the camera gradually zooms in, finally focusing on a close-up of a daisy with a few glistening dewdrops on its petals"
• "A subway rumbles past, pages flutter, the camera starts to rotate 360 degrees around the girl"
• "Sunset by the sea, waves gently lap the beach, peaceful and serene atmosphere"

• Model ID:

  doubao-seedance-1-5-pro-251215

• Features: Audio-video co-generation, highest quality
• Supported Modes: Text-to-video, image-to-video, first/last frame guidance, audio-enabled video
• Output: 480p-1080p, 24fps, 4-12 seconds
• Rate Limits: RPM 600, concurrency 10

• Model ID:

  doubao-seedance-1-0-pro-250528

• Features: High-quality standard version
• Supported Modes: Text-to-video, image-to-video, first/last frame guidance
• Output: 480p-1080p, 24fps, 2-12 seconds
• Rate Limits: RPM 600, concurrency 10

• Model ID:

  doubao-seedance-1-0-pro-fast-251015

• Features: Fast generation, lower cost
• Supported Modes: Text-to-video, image-to-video
• Output: 480p-1080p, 24fps, 2-12 seconds
• Rate Limits: RPM 600, concurrency 10

• Text-to-Video:

  doubao-seedance-1-0-lite-t2v-250428

• Image-to-Video:

  doubao-seedance-1-0-lite-i2v-250428

• Features: Faster speed, supports multi-reference images
• Rate Limits: RPM 300, concurrency 5

• Model ID:

  doubao-seedance-2-0-260128

• Features: Next-generation video generation model, comprehensive improvements in quality and performance
• Availability: ⏰ Expected to open API access at 18:00 on February 24, 2026
• Current Status: Only available in the Console Experience Center

undefined

• Cause: API Key not configured
• Solution: Follow the instructions in the "How to Configure API Key" section

• Cause: Invalid or expired API Key
• Solution: Check if the API Key is correct, or regenerate it in the console

• Cause: Parameter error (e.g., duration exceeds range)
• Solution: Check if parameters meet model requirements

• Cause: Generation time is too long or API is busy
• Solution: Increase the

  --timeout

  value, or try again later

• Cause: Violent content, unclear prompts, incorrect image format, etc.
• Solution: Check prompt content, ensure image URLs are accessible

• Cause: Exceeded RPM or concurrency limits
• Solution: Wait 1 minute and try again, or upgrade quota

• Format: MP4
• Encoding: H.264
• Resolution: 480p / 720p / 1080p (automatically selected based on model)
• Frame Rate: 24 fps
• Audio: AAC (if

  --audio

  is enabled)
• File Size: Approximately 2-5 MB/sec (1080p)

1. Clear scene description - Explain environment, time, atmosphere
2. Specific action details - Describe specific actions of objects or characters
3. Camera movement - Explain zoom, pan, tilt, close-up, etc.
4. Style specification - Specify styles like realistic, cartoon, anime, etc.

• ✅ Specific description: "Kitten chasing a butterfly" instead of "Kitten playing"
• ✅ Camera language: "Camera rotates 360 degrees" instead of "Rotate"
• ✅ Emotional atmosphere: "Warm bright sunlight" instead of "Good weather"
• ❌ Avoid vagueness: Too abstract descriptions increase randomness
• ❌ Avoid excessive length: Best to keep within 200 words
• ❌ Avoid violations: Do not include violent, pornographic, or other prohibited content

• API Reference: https://www.volcengine.com/docs/82379/1520758
• Console: https://console.volcengine.com/ark
• API Key Management: https://console.volcengine.com/ark/region:ark+cn-beijing/apikey

1. Check the error message output by the script
2. Verify if the API Key configuration is correct
3. Visit the Volcano Ark Console to view task details
4. Refer to the official documentation for more details