Kling v3.0 Std Text-to-Video API by Kuaishou
Kling v3.0 Standard Text-to-Video model by Kuaishou. High-quality video generation from text prompts.
Invoer
Uitvoer
InactiefElke uitvoering kost $0.071. Voor $10 kunt u ongeveer 140 keer uitvoeren.
U kunt doorgaan met:
Codevoorbeeld
import requests
import time
# Step 1: Start video generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "kwaivgi/kling-v3.0-std/text-to-video",
"prompt": "A beautiful sunset over the ocean with gentle waves",
"width": 512,
"height": 512,
"duration": 3,
"fps": 24,
}
generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]
# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
def check_status():
while True:
response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
result = response.json()
if result["data"]["status"] in ["completed", "succeeded"]:
print("Generated video:", result["data"]["outputs"][0])
return result["data"]["outputs"][0]
elif result["data"]["status"] == "failed":
raise Exception(result["data"]["error"] or "Generation failed")
else:
# Still processing, wait 2 seconds
time.sleep(2)
video_url = check_status()Installeren
Installeer het vereiste pakket voor uw programmeertaal.
pip install requestsAuthenticatie
Alle API-verzoeken vereisen authenticatie via een API-sleutel. U kunt uw API-sleutel ophalen via het Atlas Cloud dashboard.
export ATLASCLOUD_API_KEY="your-api-key-here"HTTP-headers
import os
API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}Stel uw API-sleutel nooit bloot in client-side code of openbare repositories. Gebruik in plaats daarvan omgevingsvariabelen of een backend-proxy.
Een verzoek indienen
import requests
url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "your-model",
"prompt": "A beautiful landscape"
}
response = requests.post(url, headers=headers, json=data)
print(response.json())Een verzoek indienen
Dien een asynchroon generatieverzoek in. De API retourneert een voorspellings-ID waarmee u de status kunt controleren en het resultaat kunt ophalen.
/api/v1/model/generateVideoVerzoekinhoud
import requests
url = "https://api.atlascloud.ai/api/v1/model/generateVideo"
headers = {
"Content-Type": "application/json",
"Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
"model": "kwaivgi/kling-v3.0-std/text-to-video",
"input": {
"prompt": "A beautiful sunset over the ocean with gentle waves"
}
}
response = requests.post(url, headers=headers, json=data)
result = response.json()
print(f"Prediction ID: {result['id']}")
print(f"Status: {result['status']}")Antwoord
{
"id": "pred_abc123",
"status": "processing",
"model": "model-name",
"created_at": "2025-01-01T00:00:00Z"
}Status controleren
Bevraag het voorspellings-eindpunt om de huidige status van uw verzoek te controleren.
/api/v1/model/prediction/{prediction_id}Polling-voorbeeld
import requests
import time
prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }
while True:
response = requests.get(url, headers=headers)
result = response.json()
status = result["data"]["status"]
print(f"Status: {status}")
if status in ["completed", "succeeded"]:
output_url = result["data"]["outputs"][0]
print(f"Output URL: {output_url}")
break
elif status == "failed":
print(f"Error: {result['data'].get('error', 'Unknown')}")
break
time.sleep(3)Statuswaarden
processingHet verzoek wordt nog verwerkt.completedDe generatie is voltooid. Resultaten zijn beschikbaar.succeededDe generatie is geslaagd. Resultaten zijn beschikbaar.failedDe generatie is mislukt. Controleer het foutveld.Voltooid antwoord
{
"data": {
"id": "pred_abc123",
"status": "completed",
"outputs": [
"https://storage.atlascloud.ai/outputs/result.mp4"
],
"metrics": {
"predict_time": 45.2
},
"created_at": "2025-01-01T00:00:00Z",
"completed_at": "2025-01-01T00:00:10Z"
}
}Bestanden uploaden
Upload bestanden naar Atlas Cloud opslag en ontvang een URL die u kunt gebruiken in uw API-verzoeken. Gebruik multipart/form-data om te uploaden.
/api/v1/model/uploadMediaUpload-voorbeeld
import requests
url = "https://api.atlascloud.ai/api/v1/model/uploadMedia"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }
with open("image.png", "rb") as f:
files = {"file": ("image.png", f, "image/png")}
response = requests.post(url, headers=headers, files=files)
result = response.json()
download_url = result["data"]["download_url"]
print(f"File URL: {download_url}")Antwoord
{
"data": {
"download_url": "https://storage.atlascloud.ai/uploads/abc123/image.png",
"file_name": "image.png",
"content_type": "image/png",
"size": 1024000
}
}Invoer-Schema
De volgende parameters worden geaccepteerd in de verzoekinhoud.
Geen parameters beschikbaar.
Voorbeeld verzoekinhoud
{
"model": "kwaivgi/kling-v3.0-std/text-to-video"
}Uitvoer-Schema
De API retourneert een voorspellingsantwoord met de gegenereerde uitvoer-URL's.
Voorbeeldantwoord
{
"id": "pred_abc123",
"status": "completed",
"model": "model-name",
"outputs": [
"https://storage.atlascloud.ai/outputs/result.mp4"
],
"metrics": {
"predict_time": 45.2
},
"created_at": "2025-01-01T00:00:00Z",
"completed_at": "2025-01-01T00:00:10Z"
}Atlas Cloud Skills
Atlas Cloud Skills integreert meer dan 300 AI-modellen rechtstreeks in uw AI-codeerassistent. Eén commando om te installeren, gebruik daarna natuurlijke taal om afbeeldingen, video's te genereren en te chatten met LLMs.
Ondersteunde clients
Installeren
npx skills add AtlasCloudAI/atlas-cloud-skillsAPI-sleutel instellen
Haal uw API-sleutel op via het Atlas Cloud dashboard en stel deze in als omgevingsvariabele.
export ATLASCLOUD_API_KEY="your-api-key-here"Mogelijkheden
Eenmaal geïnstalleerd kunt u natuurlijke taal gebruiken in uw AI-assistent om toegang te krijgen tot alle Atlas Cloud modellen.
MCP-server
De Atlas Cloud MCP-server verbindt uw IDE met meer dan 300 AI-modellen via het Model Context Protocol. Werkt met elke MCP-compatibele client.
Ondersteunde clients
Installeren
npx -y atlascloud-mcpConfiguratie
Voeg de volgende configuratie toe aan het MCP-instellingenbestand van uw IDE.
{
"mcpServers": {
"atlascloud": {
"command": "npx",
"args": [
"-y",
"atlascloud-mcp"
],
"env": {
"ATLASCLOUD_API_KEY": "your-api-key-here"
}
}
}
}Beschikbare tools
API Schema
Schema niet beschikbaarGeen voorbeelden beschikbaar
Inloggen om aanvraaggeschiedenis te bekijken
U moet ingelogd zijn om toegang te krijgen tot uw modelaanvraaggeschiedenis.
InloggenKling V3.0 Standard Text-to-Video
Kling V3.0 Standard is Kuaishou's latest text-to-video generation model, delivering cinematic video from text descriptions with optional synchronized sound and voice generation. Support for negative prompts, multiple aspect ratios, and a CFG scale for creative control.
Why Choose This?
Latest Kling generation V3.0 brings improved motion quality and visual fidelity over V2.6.
Sound generation Optional synchronized sound effects generated alongside the video.
Voice list support Add up to 2 custom voice entries for character dialogue.
Negative prompt support Exclude unwanted elements for precise control over the output.
CFG scale control Fine-tune the balance between prompt adherence and creative freedom.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the video scene and motion |
| negative_prompt | No | Elements to exclude from generation |
| duration | No | Video length: 5 or 10 seconds (default: 5) |
| aspect_ratio | No | Output ratio: 16:9 (default), 9:16, 1:1 |
| cfg_scale | No | Prompt adherence strength (default: 0.5) |
| sound | No | Generate synchronized sound (default: disabled) |
| voice_list | No | Custom voice entries, up to 2 (click "+ Add Item") |
How to Use
- Run — submit and download your video.
- Add voices (optional) — add up to 2 voice entries for character dialogue.
- Enable sound (optional) — generate synchronized audio with the video.
- Adjust cfg_scale (optional) — higher for stricter prompt following, lower for more creative freedom.
- Select aspect ratio — match your target platform.
- Set duration — 5 seconds or 10 seconds.
- Add negative prompt (optional) — specify what you want to avoid.
- Write your prompt — describe the scene, characters, motion, and style in detail.
Best Use Cases
- Storyboarding — Visualize narrative scenes with sound design.
- Marketing Videos — Produce promotional content with audio.
- Concept Visualization — Bring creative ideas to life from text.
- Social Media Content — Generate videos for TikTok, Reels, and Stories.
- Short Films — Create cinematic scenes with sound and dialogue.
Pro Tips
- Add voice_list entries for videos with character dialogue.
- Lower cfg_scale for more creative variation, higher for strict prompt adherence.
- Use negative prompts to avoid common issues (e.g., "blurry, low quality, distorted").
- Enable sound for a complete video experience with synchronized audio.
- Match aspect ratio to your platform: 16:9 for YouTube, 9:16 for TikTok/Reels, 1:1 for Instagram.
- Use the Prompt Enhancer (if available) to refine your descriptions.
Notes
- Voice list supports a maximum of 2 entries.
- Duration options are 5 or 10 seconds only.
- Only prompt is required; other parameters have defaults.
Related Models
- Kling V2.6 Standard Image-to-Video — Previous generation image-to-video.
- Kling V2.6 Standard Text-to-Video — Previous generation text-to-video.
- Kling V3.0 Standard Image-to-Video — Image-to-video with V3.0 quality.
