Kling 3.0

kwaivgi/kling-v3.0/text-to-video

kwaivgi/kling-v3.0/text-to-video. Explore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada.

Modelos relacionados

Referência completa de parâmetros, esquema de saída e preços atuais

Marketplace de APIs de modelos de IAUma plataforma para tudoMais popularTermosExplore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada.
promptPrompttextarea—≤ 5000 chars
negative_promptNegative Prompttextarea—≤ 5000 chars
durationDurationselect53 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | …
resolutionGeneration Modeselect720P720P | 1080P | 4K
aspect_ratioAspect Ratioselect16:916:9 | 9:16 | 1:1
cfg_scaleCfg Scaleslider0.50 ~ 1 · step 0.01
soundSoundbooleanfalse—
element_listElement Listarray<object>—0–3 items
↳element_idElement Idtext——
multi_shotMulti Shotboolean——
shot_typeShot Typeselect—customize | intelligence
multi_promptMulti Promptarray<object>——
↳durationDurationnumber5—
↳promptPrompttext——

Referência completa de parâmetros, esquema de saída e preços atuais

Saiba maisUma plataforma para tudoExplore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada.
videosarray<string>

API

Explore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-v3.0/text-to-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "prompt": "A futuristic cityscape at sunset with flying cars and glowing skyscrapers.",
    "negative_prompt": "Crowded streets, dull colors, and broken buildings.",
    "duration": 10,
    "resolution": "720P",
    "aspect_ratio": "16:9",
    "cfg_scale": 0.7,
    "sound": true,
    "shot_type": "intelligence"
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"
Python
import time, requests

API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1) Submit
resp = requests.post(
    "https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-v3.0/text-to-video",
    headers=HEADERS,
    json={
        "input": {
            "prompt": "A futuristic cityscape at sunset with flying cars and glowing skyscrapers.",
            "negative_prompt": "Crowded streets, dull colors, and broken buildings.",
            "duration": 10,
            "resolution": "720P",
            "aspect_ratio": "16:9",
            "cfg_scale": 0.7,
            "sound": True,
            "shot_type": "intelligence"
        }
    },
)
resp.raise_for_status()  # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()

# 2) Poll until a terminal state (completed / failed / cancelled).
#    This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
    if time.time() > deadline:
        raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
    time.sleep(3)
    poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
    poll.raise_for_status()
    task = poll.json()

print(task["status"], task.get("output"))
JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };

// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/kwaivgi/kling-v3.0/text-to-video", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "prompt": "A futuristic cityscape at sunset with flying cars and glowing skyscrapers.",
      "negative_prompt": "Crowded streets, dull colors, and broken buildings.",
      "duration": 10,
      "resolution": "720P",
      "aspect_ratio": "16:9",
      "cfg_scale": 0.7,
      "sound": true,
      "shot_type": "intelligence"
    }
  }),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();

// 2) Poll until a terminal state (completed / failed / cancelled).
//    This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
  if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
  await new Promise((r) => setTimeout(r, 3000));
  const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
  if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
  task = await poll.json();
}

console.log(task.status, task.output);

Documentação da API

Kling 3.0 Standard

High-quality text-to-video generation with cinematic visuals and synchronized audio

Kling 3.0 Standard is a cost-efficient text-to-video model designed for smooth motion, cinematic visuals, and accurate prompt adherence. With flexible duration options, multiple aspect ratios, and optional synchronized sound, it delivers ready-to-share clips at affordable pricing. The model ensures high performance with no cold starts and is accessible via a REST inference API.


🚀 Key Features

  • Cinematic Visuals: Generate videos with smooth motion and high-quality visuals directly from text prompts.
  • Flexible Duration: Create clips ranging from 3 to 15 seconds to suit various production needs.
  • Multiple Aspect Ratios: Supports 16:9 (landscape), 9:16 (portrait), and 1:1 (square) formats for diverse platforms.
  • Synchronized Audio: Optionally generate synchronized sound alongside the video for immersive experiences.
  • Precise Prompt Control: Utilize negative prompts and CFG scale for fine-tuned output.
  • Multi-Prompt Support: Chain multiple prompts for scene transitions and consistent storytelling.

🛠️ Technical Specifications

ParameterTypeDefault ValueRange/OptionsDescription
PromptString--Text description of the scene, motion, camera style, and atmosphere.
Negative PromptString--Elements to exclude from the video.
DurationInteger53–15 secondsLength of the generated video.
Aspect RatioString16:916:9, 9:16, 1:1Output format for the video.
CFG ScaleNumber0.50.0–1.0Prompt adherence strength; higher values increase relevance to the prompt.
SoundBooleanDisabledEnabled/DisabledGenerate synchronized sound alongside the video.
Shot TypeStringCustomizeCustomize, IntelligentEditing mode; customize for manual control, intelligent for auto-detection.
Multi-PromptArray--Additional prompt segments for scene transitions and progressions.
Element ListArray--Reference list of visual elements for consistency.

💰 Pricing

ResolutionAttributePrice per Second (USD)
720PMuted0.0840
720PWith Audio0.1260
1080PMuted0.1120
1080PWith Audio0.1680
4KMuted0.4200
4KWith Audio0.4200

💡 Best Use Cases

  • Social Media Content: Generate portrait or square clips for TikTok, Reels, and Shorts at scale.
  • Concept Visualization: Quickly bring creative ideas and moods to life from text descriptions.
  • Marketing & Advertising: Produce promotional video content without a film crew.
  • Prototyping: Test visual ideas and prompt variations at Standard pricing before committing to Pro.

🔗 Related Models

  • Kling V3.0 Pro Text-to-Video: Maximum quality with Pro-tier capabilities.
  • Kling V3.0 Std Image-to-Video: Animate still images at Standard pricing.
  • Kling Video O3 Std Text-to-Video: Next-generation O3 Standard text-to-video.

Pro Tips

  • The more specific your prompt, the better — include camera angle, lighting style, character behavior, and atmosphere.
  • Use negative prompts to avoid common artifacts like blurry faces or unwanted motion.
  • Match aspect ratio to your platform: 16:9 for YouTube, 9:16 for TikTok, 1:1 for Instagram.
  • Enable sound for scenes with ambient environments, crowds, or action for a more immersive result.
  • Use shorter durations (3–5s) for rapid iteration, longer (10–15s) for final output.

Notes

  • Only the prompt is a required field; all other parameters are optional.
  • Duration range: minimum 3 seconds, maximum 15 seconds.
  • Sound generation increases cost by 1.5×.
  • Use the Kling Elements tool to generate visual elements and reference their IDs in your prompts.

Modelos relacionados

xAI Grok Imagine Video v1.5 Text to Video
Texto para vídeoX Ai

xAI Grok Imagine Video v1.5 Text to Video

x-ai/grok-imagine-video-v1.5/text-to-video. Explore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada.

a partir de $0.840 / por execução
MiniMax H3 Text to Video
Texto para vídeoMinimax

MiniMax H3 Text to Video

minimax/h3/text-to-video. Explore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada.

a partir de $0.650 / por execução
ltx-2.5/text-to-video
Texto para vídeoLtx 2.5

ltx-2.5/text-to-video

ltx-2.5/text-to-video. Explore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada.

a partir de $0.500 / por execução
Kling Omni Video O3 Standard Text-To-Video
Texto para vídeoKling

Kling Omni Video O3 Standard Text-To-Video

kwaivgi/kling-video-o3/text-to-video. Explore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada.

a partir de $0.420 / por execução
Kling V2.6 Text to Video API
Texto para vídeoKling

Kling V2.6 Text to Video API

kwaivgi/kling-v2.6/text-to-video. Explore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada.

a partir de $0.210 / por execução
Gemini Omni Flash Text to Video API
Texto para vídeoGoogle

Gemini Omni Flash Text to Video API

google/gemini-omni-flash/text-to-video. Explore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada.

a partir de $1.04 / por execução
Seedance 2.0 Mini Text to Video
Texto para vídeoDoubao

Seedance 2.0 Mini Text to Video

doubao/seedance-2.0-mini/text-to-video. Explore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada.

a partir de $0.378 / por execução
Seedance 2.5 Text-to-Video
Texto para vídeoDoubao

Seedance 2.5 Text-to-Video

doubao/seedance-2-5/text-to-video. Explore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada.

a partir de $1.155 / por execução