API-Schlüssel holen

von Kuaishou

4K-Clips, Multi-Shot-Schnitte und Bewegungssteuerung

kling/3.0/text-to-videoAb 51 Creditsfür einen 5-Sekunden-Clip · 0,51 $
  • Bis 4K
  • Clips mit 3–15 s
  • Mit Ton
  • Start- und Endbild
  • 3 Seitenverhältnisse
  • Video erstellen
  • Bild zu Video
  • Bewegungssteuerung
Beispiele ansehen

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.

Modellnamekling/3.0/text-to-video
EndpunktPOST 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"

Der input ist aus dem Schema unten gebaut und besteht die Prüfung so, wie er dasteht. Ersetz Prompt und Links durch deine eigenen.

Preis

OptionCredits pro Sekunde≈ USD
generate_audio falseresolution 720p10,080,10 $
generate_audio falseresolution 1080p13,440,13 $
generate_audio trueresolution 720p15,120,15 $
generate_audio trueresolution 1080p20,160,20 $
generate_audio falseresolution 4K50,40,50 $
generate_audio trueresolution 4K50,40,50 $

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.

  • promptstringPflicht

    Describe the scene, the action and the camera. With sound on, add dialogue in quotes and the sounds you want.

    Bereich
    1 – 2500 chars
  • negative_promptstringOptional

    Was du nicht sehen willst.

    Bereich
    0 – 2500 chars
  • aspect_ratiostringOptional

    Die Form des Bildes: breit, quadratisch oder hoch.

    Standardwert
    "16:9"
    Erlaubte Werte
    "16:9""9:16""1:1"
  • resolutionstringOptionalÄndert den Preis

    Ausgabegröße. Größere Formate sind schärfer und kosten mehr.

    Standardwert
    "720p"
    Erlaubte Werte
    "720p""1080p""4k"
  • generate_audiobooleanOptionalÄndert den Preis

    Fügt passenden Ton hinzu: Stimmen, Atmo und Effekte.

    Standardwert
    false
  • duration_secondsintegerOptionalÄndert den Preis

    Wie lang der Clip läuft. Abgerechnet wird pro Sekunde.

    Standardwert
    5
    Bereich
    3 – 15
  • shot_typestringOptional

    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.

    Standardwert
    "single"
    Erlaubte Werte
    "single""multi""customize"
  • multi_promptarray<object>Manchmal Pflicht

    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.

    Bereich
    1 – 6 items
    Felder darin
    • multi_prompt[].promptstringPflicht

      What happens in this shot, up to 512 characters.

      Bereich
      1 – 512 chars
    • multi_prompt[].duration_secondsintegerPflicht

      Length of this shot in whole seconds, 1 to 15.

      Bereich
      1 – 15
  • guidance_scalenumberOptional

    Wie streng das Modell dem Prompt folgt.

    Standardwert
    0.5
    Bereich
    0 – 1
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

PromptNight 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.
Dieselbe Anfrage über die API
{
  "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
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
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
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

JSON
{
  "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

Node.js
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
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.