Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →video-production-buddy/ai-video-gen
Generate AI videos from text prompts using multiple provider gateways.
Passed 20 of 20 test cases with the skill, and 9 of 20 without it.
and 17 more in the full report
12 fixed10 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
What is the allowed clip duration range in seconds when generating videos using MuAPI Seedance 2?
| Checked | Without skill | With skill |
|---|---|---|
| States 4 to 15 seconds as the allowed video duration range on MuAPI. | Missed | Passed |
The instructions your model reads when the skill loads.
Generate AI videos from text prompts through the configured gateway:
| Gateway | Env Variable | Providers | Tool |
|---|---|---|---|
| fal.ai | FAL_KEY | Seedance 2.0 (standard + fast), Kling v3/v2.1, MiniMax, VEO | seedance_video, kling_video, minimax_video, veo_video |
| HeyGen | HEYGEN_API_KEY | VEO 3.1, Kling Pro, Sora v2, Runway Gen-4, Seedance Pro / Lite (1.x) | heygen_video |
| MuAPI | MUAPI_API_KEY or MU_API_KEY | Seedance 2 text-to-video and image-to-video (standard + fast) | muapi_video |
Preferred premium default — Seedance 2.0. When any premium gateway is configured (FAL_KEY → seedance_video, or HeyGen's Video Agent / Avatar Shots path), Seedance 2.0 is the preferred default for cinematic, trailer, and high-fidelity clip work. It is the only model in the fleet with single-pass native synchronized audio, multi-shot generation, director-level camera control, and lip-sync from quoted dialogue, and it ranks #1 on Artificial Analysis Elo as of early 2026. Switch off it only when the user has a specific reason (budget, provider preference, stylistic fit like VEO for photoreal landscape or Kling for specific anime look). See Layer 3 seedance-2-0 for the authoritative prompting and parameter guide.
IMPORTANT: Always use video_selector instead of calling provider tools directly. The selector handles availability checks, cost comparison, and automatic fallback, and its scoring engine already biases toward Seedance 2.0 for cinematic intent.
Use whichever configured gateway best matches the user's available providers and cost/quality goals.
HEYGEN_API_KEY to access the multi-model gateway.FAL_KEY to access Kling, MiniMax, and Veo through fal.ai.MUAPI_API_KEY or MU_API_KEY. Use the MuAPI route below;
the HeyGen endpoints and examples in this guide do not apply to MuAPI.Use video_selector with preferred_provider: "muapi" (and
allowed_providers: ["muapi"] when the task permits only this provider).
Supported operations are text_to_video and image_to_video; model variants
are seedance-2-text-to-video, seedance-2-image-to-video, and their -fast
variants. Duration is 4–15 seconds.
For a local reference image, pass reference_image_path to the selector. It
maps to MuAPI's image_path, validates JPEG/PNG/WebP up to 10 MiB, and uploads
directly to MuAPI with the MuAPI key. Do not upload that image through fal.ai
or HeyGen. An existing image_url can be used instead. FFmpeg/ffprobe must be
installed; use an .mp4 output below projects/<project-name>/assets/ or
renders/. See docs/PROVIDERS.md#muapi for setup and download constraints.
test cases passed, vs 9 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.