4K-Clips, Multi-Shot-Schnitte und Bewegungssteuerung
- Bis 4K
- Clips mit 3–15 s
- Mit Ton
- Start- und Endbild
- 3 Seitenverhältnisse
- Video erstellen
- Bild zu Video
- Bewegungssteuerung
Du rufst es mit dem Modellnamen kling/3.0/text-to-video über POST /jobs/createTask auf, ab 51 Credits für einen 5-Sekunden-Clip (0,51 $). Neue Konten bekommen 30 kostenlose Credits, damit du es zuerst im Playground testen kannst.
kling/3.0/text-to-videoPOST https://api.popnow.ai/api/v1/jobs/createTask# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $IDEMPOTENCY_KEY" \
-d '{
"model": "kling/3.0/text-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration_seconds": 5,
"shot_type": "single"
}
}'
# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $POPNOW_API_KEY"// Node 18+ (or any runtime with fetch). Keep the API key on your server.
const BASE = "https://api.popnow.ai/api/v1";
const headers = { Authorization: `Bearer ${process.env.POPNOW_API_KEY}` };
const sleep = (ms) => new Promise((r) => setTimeout(r, ms));
async function call(path, init = {}) {
const res = await fetch(BASE + path, { ...init, headers: { ...headers, ...init.headers } });
const body = await res.json();
if (body.code !== 200) throw new Error(`${body.code} ${body.msg}`);
return body.data;
}
const { taskId } = await call("/jobs/createTask", {
method: "POST",
headers: { "Content-Type": "application/json", "Idempotency-Key": crypto.randomUUID() },
body: JSON.stringify({
"model": "kling/3.0/text-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration_seconds": 5,
"shot_type": "single"
}
}),
});
// Poll with backoff. A finished task may still be copying files: wait while an asset is pending.
let task;
for (let delay = 2000; ; delay = Math.min(delay * 1.5, 15000)) {
await sleep(delay);
task = await call(`/jobs/recordInfo?taskId=${taskId}`);
const copying = (task.output?.assets ?? []).some((a) => a.pending && !a.unavailable);
if (["succeeded", "failed", "canceled", "expired"].includes(task.state) && !copying) break;
}
if (task.state !== "succeeded") throw new Error(`${task.state}: ${task.errorMessage ?? "no detail"}`);
// Each asset has a signed url (no API key needed) that expires at expiresAt: save the file.
for (const asset of task.output.assets) console.log(asset.url);import os, time, uuid, requests
BASE = "https://api.popnow.ai/api/v1"
HEADERS = {"Authorization": f"Bearer {os.environ['POPNOW_API_KEY']}"}
def call(method, path, **kwargs):
body = requests.request(method, BASE + path, headers={**HEADERS, **kwargs.pop("headers", {})}, timeout=30, **kwargs).json()
if body["code"] != 200:
raise RuntimeError(f'{body["code"]} {body["msg"]}')
return body["data"]
task_id = call(
"POST",
"/jobs/createTask",
headers={"Idempotency-Key": str(uuid.uuid4())}, # reuse it if you retry
json={
"model": "kling/3.0/text-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration_seconds": 5,
"shot_type": "single"
}
},
)["taskId"]
# Poll with backoff. A finished task may still be copying files: wait while an asset is pending.
delay = 2.0
while True:
time.sleep(delay)
task = call("GET", "/jobs/recordInfo", params={"taskId": task_id})
assets = (task.get("output") or {}).get("assets") or []
copying = any(a.get("pending") and not a.get("unavailable") for a in assets)
if task["state"] in ("succeeded", "failed", "canceled", "expired") and not copying:
break
delay = min(delay * 1.5, 15.0)
if task["state"] != "succeeded":
raise RuntimeError(f'{task["state"]}: {task.get("errorMessage", "no detail")}')
# Each asset has a signed url (no API key needed) that expires at expiresAt: save the file.
for asset in assets:
print(asset["url"])Der input ist aus dem Schema unten gebaut und besteht die Prüfung so, wie er dasteht. Ersetz Prompt und Links durch deine eigenen.
Preis
| Option | Credits pro Sekunde | ≈ USD |
|---|---|---|
generate_audio falseresolution 720p | 10,08 | 0,10 $ |
generate_audio falseresolution 1080p | 13,44 | 0,13 $ |
generate_audio trueresolution 720p | 15,12 | 0,15 $ |
generate_audio trueresolution 1080p | 20,16 | 0,20 $ |
generate_audio falseresolution 4K | 50,4 | 0,50 $ |
generate_audio trueresolution 4K | 50,4 | 0,50 $ |
1 Credit = 0,01 $ · Alle Optionen und Preise: GET /models/kling/3.0/text-to-video
Jede Aufgabe wird auf ganze Credits aufgerundet, ein Lauf in der günstigsten Stufe kostet also 51 Credits für einen 5-Sekunden-Clip (0,51 $).
Limits
- Cliplänge
- 3–15 s
- Auflösungen
- 720p · 1080p · 4K
- Seitenverhältnisse
- 16:9 · 9:16 · 1:1
- Prompt-Länge (Zeichen)
- 2,500
Parameter
Diese Felder stammen aus demselben Schema, gegen das wir jede Anfrage prüfen. Nicht aufgeführte Felder werden abgelehnt.
Manche Felder hängen voneinander ab (zum Beispiel mindestens eine Referenz). Die genauen Regeln stehen im rohen Schema ganz unten.
promptstringPflichtDescribe the scene, the action and the camera. With sound on, add dialogue in quotes and the sounds you want.
negative_promptstringOptionalWas du nicht sehen willst.
aspect_ratiostringOptionalDie Form des Bildes: breit, quadratisch oder hoch.
resolutionstringOptionalÄndert den PreisAusgabegröße. Größere Formate sind schärfer und kosten mehr.
generate_audiobooleanOptionalÄndert den PreisFügt passenden Ton hinzu: Stimmen, Atmo und Effekte.
duration_secondsintegerOptionalÄndert den PreisWie lang der Clip läuft. Abgerechnet wird pro Sekunde.
shot_typestringOptionalsingle keeps one continuous shot; multi lets the model cut the prompt into several shots on its own; customize follows the shot list you give in multi_prompt.
multi_promptarray<object>Manchmal PflichtShot list for shot_type customize: one entry per shot, in order, each with its own prompt and length in seconds. The lengths must add up to duration_seconds.
Felder darin
multi_prompt[].promptstringPflichtWhat happens in this shot, up to 512 characters.
multi_prompt[].duration_secondsintegerPflichtLength of this shot in whole seconds, 1 to 15.
guidance_scalenumberOptionalWie streng das Modell dem Prompt folgt.
Rohes JSON-Schema
{
"type": "object",
"allOf": [
{
"if": {
"required": [
"shot_type"
],
"properties": {
"shot_type": {
"const": "customize"
}
}
},
"then": {
"required": [
"multi_prompt"
]
}
}
],
"required": [
"prompt"
],
"properties": {
"prompt": {
"type": "string",
"maxLength": 2500,
"minLength": 1,
"description": "Describe the scene, the action and the camera. With sound on, add dialogue in quotes and the sounds you want."
},
"shot_type": {
"enum": [
"single",
"multi",
"customize"
],
"type": "string",
"default": "single",
"description": "single keeps one continuous shot; multi lets the model cut the prompt into several shots on its own; customize follows the shot list you give in multi_prompt."
},
"resolution": {
"enum": [
"720p",
"1080p",
"4k"
],
"type": "string",
"default": "720p",
"description": "Output resolution. Higher tiers cost more per second."
},
"aspect_ratio": {
"enum": [
"16:9",
"9:16",
"1:1"
],
"type": "string",
"default": "16:9",
"description": "Output aspect ratio."
},
"multi_prompt": {
"type": "array",
"items": {
"type": "object",
"required": [
"prompt",
"duration_seconds"
],
"properties": {
"prompt": {
"type": "string",
"maxLength": 512,
"minLength": 1,
"description": "What happens in this shot, up to 512 characters."
},
"duration_seconds": {
"type": "integer",
"maximum": 15,
"minimum": 1,
"description": "Length of this shot in whole seconds, 1 to 15."
}
},
"additionalProperties": false
},
"maxItems": 6,
"minItems": 1,
"description": "Shot list for shot_type customize: one entry per shot, in order, each with its own prompt and length in seconds. The lengths must add up to duration_seconds."
},
"generate_audio": {
"type": "boolean",
"default": false,
"description": "Generate a native soundtrack (voices, effects, ambience) with the picture. Audio costs more per second."
},
"guidance_scale": {
"type": "number",
"default": 0.5,
"maximum": 1,
"minimum": 0,
"description": "How closely the clip follows the prompt, from 0 to 1. Higher sticks to the prompt more; lower gives the model more freedom."
},
"negative_prompt": {
"type": "string",
"maxLength": 2500,
"description": "What to keep out of the clip: objects, looks or motion you do not want."
},
"duration_seconds": {
"type": "integer",
"default": 5,
"maximum": 15,
"minimum": 3,
"description": "Output length in whole seconds, from 3 to 15. Billed per second."
}
},
"additionalProperties": false
}Ein echtes Ergebnis von Kling 3.0
Night on the marble terrace of a Venetian palazzo during a gala. A woman in her early thirties in a backless emerald silk gown walks away from the camera toward the balustrade, candlelight catching the line of her back, the Grand Canal glittering below. She stops, looks back over her shoulder at the camera and says with a faint smile, "Don't wait up." Slow tracking shot behind her, shallow depth of field. Sound: a string quartet playing inside, the murmur of guests, water lapping against stone.
{
"model": "kling/3.0/text-to-video",
"input": {
"prompt": "Night on the marble terrace of a Venetian palazzo during a gala. A woman in her early thirties in a backless emerald silk gown walks away from the camera toward the balustrade, candlelight catching the line of her back, the Grand Canal glittering below. She stops, looks back over her shoulder at the camera and says with a faint smile, \"Don't wait up.\" Slow tracking shot behind her, shallow depth of field. Sound: a string quartet playing inside, the murmur of guests, water lapping against stone.",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration_seconds": 5,
"shot_type": "single",
"generate_audio": true
}
}Antworten, Polling und Callbacks
Alle Modelle funktionieren gleich: Task anlegen, dann pollen oder auf den Callback warten.
Erst den Preis prüfen
curl -X POST https://api.popnow.ai/api/v1/jobs/quote \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kling/3.0/text-to-video",
"input": {
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
"aspect_ratio": "16:9",
"resolution": "720p",
"duration_seconds": 5,
"shot_type": "single"
}
}'Gleicher Body wie bei createTask. Liefert die erwartete und die höchstmögliche Abbuchung und startet nichts.
Angenommen
HTTP/1.1 202 Accepted
{
"code": 200,
"msg": "success",
"data": {
"taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
"state": "queued"
},
"request_id": "req_example_create"
}HTTP 202 heißt: Der Task ist angenommen, die Credits sind reserviert, aber noch nicht abgebucht. Die endgültige Abbuchung liegt nie über der Reservierung.
Status abfragen
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $POPNOW_API_KEY"Frag alle paar Sekunden mit wachsendem Abstand ab und hör auf, sobald state succeeded, failed, canceled oder expired ist.
Fertiger Task
{
"code": 200,
"msg": "success",
"data": {
"taskId": "task_01k3m8x9q2z4v7n5p6r8s0t1w3",
"model": "kling/3.0/text-to-video",
"state": "succeeded",
"output": {
"assets": [
{
"url": "https://cdn.popnow.ai/tasks/task_01k3m8x9q2z4v7n5p6r8s0t1w3/output.mp4?signature=FROM_RESPONSE",
"expiresAt": "2026-10-17T12:20:00Z",
"mime": "video/mp4",
"width": 1280,
"height": 720,
"durationSeconds": 5
}
]
},
"settled": true
},
"request_id": "req_example_record"
}Lad über die url vor expiresAt herunter. Später einen frischen Link nötig? Frag POST /common/download-url.
Callback prüfen
import { createHash, createHmac, timingSafeEqual } from "node:crypto";
import express from "express";
const app = express();
// express.raw keeps the exact bytes that were signed; express.json would not match.
app.post("/hooks/popnow", express.raw({ type: "application/json" }), (req, res) => {
const timestamp = req.header("X-Webhook-Timestamp");
const signature = req.header("X-Webhook-Signature") ?? "";
const body = JSON.parse(req.body.toString("utf8"));
const taskId = body.data?.taskId ?? body.task_id;
const digest = createHash("sha256").update(req.body).digest("hex");
const expected = createHmac("sha256", process.env.POPNOW_WEBHOOK_SECRET)
.update(`${taskId}.${timestamp}.${digest}`)
.digest("base64");
const ok = expected.length === signature.length && timingSafeEqual(Buffer.from(expected), Buffer.from(signature));
// Check the signature first, then reject anything older than five minutes.
if (!ok || Math.abs(Date.now() / 1000 - Number(timestamp)) > 300) return res.status(401).end();
res.status(200).end(); // answer fast, then fetch the task and store its files
});Mit gesetzter callBackUrl schicken wir dir den fertigen Task. Prüf die Signatur am rohen Body, bevor du ihm vertraust.
Lokale Datei schicken
curl -X POST https://api.popnow.ai/api/v1/common/upload-url \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{"contentType": "image/png", "bytes": 482113}'
# PUT the file bytes to data.uploadUrl with every header in data.headers, then commit it:
curl -X POST https://api.popnow.ai/api/v1/files/$FILE_ID/commit \
-H "Authorization: Bearer $POPNOW_API_KEY"
# The commit returns a popnow://f/... reference. Put it in any image, video or
# audio field of the task input instead of a public https URL.Öffentliche https-Links funktionieren direkt. Lokale Dateien laufen vorher über upload-url und commit.