Kling 3.0 video generation on PoYo / poyo.ai via `https://api.poyo.ai/api/generate/submit`; use for `kling-3.0/standard`, `kling-3.0/pro`, text-to-video, ima...
Design & media
kling
Try itGenerate and edit video with Kling through RunAPI. Use when the user asks an agent to create, edit, or transform video with Kling. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.
What it does
Generate and edit video with Kling through RunAPI. Use when the user asks an agent to create, edit, or transform video with Kling. Default to the RunAPI CLI for one-off generation; use SDKs only when the user is integrating RunAPI into an app or backend.
The skill document
Kling on RunAPI
Choose route
- For a one-off artifact or result, use the registered
klingservice in therunapiCLI. If the installed command catalog does not list it, stop and report the missing service instead of inventing a command. - For an app, backend, worker, library, webhook pipeline, or production codebase, go directly to Integrate with SDK. Never shell out to the CLI as the production runtime.
Discover contract
Authenticate, then inspect the installed command catalog and the selected operation's current contract:
runapi auth status > auth.json
jq -e '.authenticated == true' auth.json
runapi kling --help
runapi kling --help
curl --fail --location https://runapi.ai/docs/api/kling/.md --output contract.md
If authentication is false, stop before submitting. Ask the user to provide a valid RUNAPI_API_KEY, or import a user-provided key from stdin with runapi auth import-token --token -; use interactive browser login only when the user explicitly requests it. Choose `` only from service help. Treat command help as authoritative for the installed operation, model, and top-level field roster. Treat its API Reference as authoritative for the complete request schema, nested fields, conditional rules, task behavior, and response variants. If the two surfaces disagree, stop and report the contract mismatch instead of guessing.
Build request
Create request.json as valid JSON using only fields accepted by the discovered operation contract. For the chosen model and values, evaluate every applicable conditional rule as a set: satisfy every required field, omit every forbidden field, and stop on unresolved contradictions.
Traverse nested objects and arrays before execution. Close every relationship stated by the discovered contract, including uniqueness constraints and cross-references between nested values.
For a discovered local media input, including file-typed fields and top-level media URL fields, put an agent-readable local file path directly in request.json. The CLI consumes file fields as declared and uploads local paths in top-level media URL fields. Use runapi files create only when the user needs a reusable URL, provides Base64, or the discovered contract explicitly requires a separate upload.
Validate the file before sending it:
jq empty request.json
Execute
Submit exactly once and persist the task response before waiting:
runapi kling --async --input-file request.json > task.json
task_id="$(jq -er '.id' task.json)"
For a one-off result, immediately wait for that same task and save the complete JSON response. This blocking wait is the default:
runapi wait "$task_id" --service kling --action > result.json
Only when the user explicitly asks for background execution, polling, or webhook integration may you stop after validating task.json. Report the task id and do not claim that the deliverable is complete.
Verify
A success status is not the deliverable. Read and validate the complete response according to the discovered result contract. Preserve the complete non-media result in the exact requested format, including JSON, text, SRT, or VTT.
For every requested media deliverable listed anywhere in the response, download all of them rather than returning only the first URL. Before downloading, derive its expected MIME type or family from response metadata when present, then the selected output format, then an unambiguous result field such as videos, images, or audios in the API Reference. The Catalog-declared fallback families for this skill are video/*. Stop only when no single expected type or family can be established from those sources.
For every downloaded file, require both a non-empty file and the expected MIME type or family:
curl --fail --location --output
for file in ; do
expected_mime=
test -s "$file"
[[ "$(file --brief --mime-type "$file")" == $expected_mime ]]
done
Do not report completion when any requested deliverable is missing, empty, or has an unexpected MIME type. Record Skill Conformance separately from Task Outcome so a service failure does not hide whether this recipe was followed.
Recover or stop
- Correct a request shape at most once, and only when the discovered contract or returned validation error identifies the correction.
- Retry a transient transport failure at most once, and only when evidence confirms that no task was created, no billing occurred, and retrying is safe.
- If waiting times out or loses transport after
task.jsonexists, preserve the error and rerunrunapi waitfor that same task at most once. Never submit a replacement task. - On a terminal RunAPI or service failure, preserve the task/error evidence and stop. Keep the selected model and capability, and do not submit another paid request without user authorization.
- If the contract is missing a fact required to build or verify the request, stop and report the contract gap. Do not turn a product defect into a permanent skill workaround.
Integrate with SDK
Use this route only for application or production-code integration. Open the current RunAPI SDK reference below, select the package for the target language and Kling, and confirm its install command, client methods, request types, response types, and error classes before coding. Build the request from the same discovered product contract and apply the same deliverable verification and stop rules. Do not invoke runapi as a subprocess from production code.
References
- Model overview, pricing, and rate limits: https://runapi.ai/models/kling.md
- Provider overview: https://runapi.ai/providers/kuaishou.md
- Full model catalog: https://runapi.ai/models.md
- SDK integration: https://github.com/runapi-ai/kling-sdk
Variants
kling-3.0: https://runapi.ai/models/kling/3.0.mdkling-ai-avatar-pro: https://runapi.ai/models/kling/ai-avatar-pro.mdkling-ai-avatar-standard: https://runapi.ai/models/kling/ai-avatar-standard.mdkling-ai-avatar-v1-pro: https://runapi.ai/models/kling/ai-avatar-v1-pro.mdkling-o1: https://runapi.ai/models/kling/o1.mdkling-v1-avatar-standard: https://runapi.ai/models/kling/v1-avatar-standard.mdkling-v2.1-master-image-to-video: https://runapi.ai/models/kling/v2.1-master-image-to-video.mdkling-v2.1-master-text-to-video: https://runapi.ai/models/kling/v2.1-master-text-to-video.mdkling-v2.1-pro: https://runapi.ai/models/kling/v2.1-pro.mdkling-v2.1-standard: https://runapi.ai/models/kling/v2.1-standard.mdkling-v2.5-turbo-image-to-video-pro: https://runapi.ai/models/kling/v2.5-turbo-image-to-video-pro.mdkling-v2.5-turbo-text-to-video-pro: https://runapi.ai/models/kling/v2.5-turbo-text-to-video-pro.mdkling-v2.6: https://runapi.ai/models/kling/v2.6.mdkling-v3-omni: https://runapi.ai/models/kling/v3-omni.mdkling-v3-turbo-image-to-video: https://runapi.ai/models/kling/v3-turbo-image-to-video.mdkling-v3-turbo-text-to-video: https://runapi.ai/models/kling/v3-turbo-text-to-video.md
Related skills
Kling 3.0 video generation on RunComfy. Kling 3.0 (also called Kling V3.0) is Kuaishou Technology's third-generation multi-shot video model with native synchronized audio and consistent character identity across shots. This skill covers all six Kling 3.0 endpoints, spanning three rendering tiers (Standard, Pro, 4K) and two modes (text-to-video, image-to-video). Calls runcomfy run kling/kling-3.0/<tier>/<mode> through the local RunComfy CLI. Triggers on "kling", "kling 3.0", "kling v3", "kling pro", "kling 4k", "kling text to video", "kling image to video", or any explicit ask to generate or animate with Kling 3.0.
Use APIDot for Kling 3.0 API workflows, including Kling 3.0 Standard, Kling 3.0 Pro, Kling 3.0 4K, text-to-video API, image-to-video API, multi-shot video, N...
Use APIDot for Kling 2.1 API workflows, including Kling 2.1 Standard, Kling 2.1 Pro, image-to-video API, start-frame guidance, optional end-frame control, as...
Use APIDot for Kling 2.6 API workflows, including text-to-video API, image-to-video API, native audio video generation, prompt-driven clips, async task submi...
Powerful video generation with Kling v3. Supports high-quality text-to-video and image-to-video. 使用可灵 (Kling) v3 强大的视频生成模型,支持高质量的文生视频与图生视频。