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 IA | Uma plataforma para tudo | Mais popular | Termos | Explore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada. |
|---|---|---|---|---|
| promptPrompt | textarea | — | ≤ 5000 chars | |
| negative_promptNegative Prompt | textarea | — | ≤ 5000 chars | |
| durationDuration | select | 5 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | … | |
| resolutionGeneration Mode | select | 720P | 720P | 1080P | 4K | |
| aspect_ratioAspect Ratio | select | 16:9 | 16:9 | 9:16 | 1:1 | |
| cfg_scaleCfg Scale | slider | 0.5 | 0 ~ 1 · step 0.01 | |
| soundSound | boolean | false | — | |
| element_listElement List | array<object> | — | 0–3 items | |
| ↳element_idElement Id | text | — | — | |
| multi_shotMulti Shot | boolean | — | — | |
| shot_typeShot Type | select | — | customize | intelligence | |
| multi_promptMulti Prompt | array<object> | — | — | |
| ↳durationDuration | number | 5 | — | |
| ↳promptPrompt | text | — | — |
Referência completa de parâmetros, esquema de saída e preços atuais
| Saiba mais | Uma plataforma para tudo | Explore APIs de modelos de imagem, vídeo e troca de rosto. Teste qualquer modelo e integre-o por uma API REST unificada. |
|---|---|---|
| videos | array<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
| Parameter | Type | Default Value | Range/Options | Description |
|---|---|---|---|---|
| Prompt | String | - | - | Text description of the scene, motion, camera style, and atmosphere. |
| Negative Prompt | String | - | - | Elements to exclude from the video. |
| Duration | Integer | 5 | 3–15 seconds | Length of the generated video. |
| Aspect Ratio | String | 16:9 | 16:9, 9:16, 1:1 | Output format for the video. |
| CFG Scale | Number | 0.5 | 0.0–1.0 | Prompt adherence strength; higher values increase relevance to the prompt. |
| Sound | Boolean | Disabled | Enabled/Disabled | Generate synchronized sound alongside the video. |
| Shot Type | String | Customize | Customize, Intelligent | Editing mode; customize for manual control, intelligent for auto-detection. |
| Multi-Prompt | Array | - | - | Additional prompt segments for scene transitions and progressions. |
| Element List | Array | - | - | Reference list of visual elements for consistency. |
💰 Pricing
| Resolution | Attribute | Price per Second (USD) |
|---|---|---|
| 720P | Muted | 0.0840 |
| 720P | With Audio | 0.1260 |
| 1080P | Muted | 0.1120 |
| 1080P | With Audio | 0.1680 |
| 4K | Muted | 0.4200 |
| 4K | With Audio | 0.4200 |
💡 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
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.
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.
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.
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.
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.
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.
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.
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.