Browse ModelsKwaivgiKwaivgi Kling V3.0 Pro Text To Video

Kwaivgi Kling V3.0 Pro Text To Video

Kwaivgi Kling V3.0 Pro Text To Video

Playground

Try it on WavespeedAI!

Kling 3.0 Pro delivers top-tier text-to-video generation with smooth motion, cinematic visuals, accurate prompt adherence, and native audio for ready-to-share clips. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

Features

Kling V3.0 Pro Text-to-Video

Kling V3.0 Pro is Kuaishou’s highest-quality text-to-video model, delivering superior visual fidelity and motion realism over the Standard tier. With synchronized sound generation, voice support, and precise creative controls, it produces cinematic-grade video from text descriptions.


Why Choose This?

  • Pro-tier quality Superior visual detail, motion smoothness, and cinematic rendering compared to Standard.

  • 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

ParameterRequiredDescription
promptYesText description of the video scene and motion
negative_promptNoElements to exclude from generation
durationNoVideo length: 5 or 10 seconds (default: 5)
aspect_ratioNoOutput ratio: 16:9 (default), 9:16, 1:1
cfg_scaleNoPrompt adherence strength (default: 0.5)
soundNoGenerate synchronized sound (default: disabled)
voice_listNoCustom voice entries, up to 2 (click ”+ Add Item”)

How to Use

  1. Write your prompt — describe the scene, characters, motion, and style in detail.
  2. Add negative prompt (optional) — specify what you want to avoid.
  3. Set duration — 5 seconds or 10 seconds.
  4. Select aspect ratio — match your target platform.
  5. Adjust cfg_scale (optional) — higher for stricter prompt following, lower for more freedom.
  6. Enable sound (optional) — generate synchronized audio with the video.
  7. Add voices (optional) — add up to 2 voice entries for character dialogue.
  8. Run — submit and download your video.

Pricing

DurationSound OffSound On
5s$0.24$0.36
10s$0.48$0.72

Billing Rules

  • Sound multiplier: disabled = 1×, enabled = 1.5×

Best Use Cases

  • High-End Production — Cinematic scenes requiring maximum visual quality.
  • Professional Marketing — Premium promotional videos with sound design.
  • Short Films — Create film-quality scenes with dialogue and sound.
  • Brand Content — Polished visual storytelling for brand campaigns.
  • Creative Direction — Explore high-fidelity concepts for pre-production.

Pro Tips

  • Use the Prompt Enhancer to refine your descriptions automatically.
  • Include cinematography terms (handheld, rim light, backlight, depth of field) for more cinematic results.
  • Enable sound for a complete video experience with synchronized audio.
  • Use negative prompts to avoid common issues (e.g., “blurry, low quality, distorted”).
  • Match aspect ratio to your platform: 16:9 for YouTube, 9:16 for TikTok/Reels, 1:1 for Instagram.
  • Use Standard tier for drafts and testing, Pro for final production.

Notes

  • Only prompt is required; other parameters have defaults.
  • Duration options are 5 or 10 seconds only.
  • Voice list supports a maximum of 2 entries.
  • Sound generation increases cost by 1.5×.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v3.0-pro/text-to-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "duration": 5,
    "aspect_ratio": "16:9",
    "cfg_scale": 0.5
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-The positive prompt for the generation.
negative_promptstringNo-The negative prompt for the generation.
durationintegerNo55, 10The duration of the generated media in seconds.
aspect_ratiostringNo16:916:9, 9:16, 1:1The aspect ratio of the generated video.
cfg_scalenumberNo0.50.00 ~ 1.00Flexibility in video generation; The higher the value, the lower the model's degree of flexibility, and the stronger the relevance to the user's prompt.
soundbooleanNo--Whether sound is generated simultaneously when generating a video.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsstringArray of URLs to the generated content.
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.