Kwaivgi Kling V2.6 Pro Image To Video
Playground
Try it on WavespeedAI!Kling 2.6 Pro: Top-tier image-to-video generation with unmatched motion fluidity, cinematic visuals, and exceptional prompt precision, offering superior quality at an unbeatable value, and native audio generation.
Features
Kling 2.6 Audio Model - Image to Video
Kling 2.6 introduces audio–video co-generation for the very first time, pairing superb visuals with natural, native audio to deliver a fully coherent, immersive experience — more than just a video clip.
Model Highlights
- Audio–video co-generation introduced for the very first time in the Kling series.
- Voices that sync flawlessly with the character — natural, native, and instantly immersive.
- Generates an entire experience, not just a clip — coherent looking & sounding output that opens up rich narrative possibilities.
- When superb visuals are paired with natural voiceovers, matching sound effects, and immersive ambient sounds, the 2.6 model generates coherent looking & sounding outputs as an entire experience — more than a video clip.
Aspect Ratios
Kling 2.6 supports the following aspect ratios:
- 16:9 – Standard landscape video (YouTube, web, most displays)
- 9:16 – Vertical video (TikTok, Reels, Shorts, Stories)
- 1:1 – Square video (feeds, social posts, ads)
Use Cases
- Marketing and launch videos with native, character-synced voiceover.
- Storytelling and narrative content where visuals and audio must feel like one.
- Product explainers and demo videos with both strong visuals and natural narration.
- Cinematic social media content with immersive ambient sound and effects.
Price
- Without Audio 5s video – $0.35
- Without Audio 10s video – $0.70
- With Audio 5s video – $0.70
- With Audio 10s video – $1.40
How to Use
- Describe your desired scene, characters, motion, and audio mood (voiceover tone, ambience, SFX).
- Choose an aspect ratio (16:9, 9:16, or 1:1) and configure video duration (e.g., 5s or 10s).
- Run generation to create a coherent audio–video experience — See the Sound, Hear the Visual.
- Refine and regenerate as needed for alternative versions or platforms.
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-v2.6-pro/image-to-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
"sound": true,
"duration": 5
}'
# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | No | - | The positive prompt for the generation. | |
| negative_prompt | string | No | - | The negative prompt for the generation. | |
| image | string | No | - | Supported image formats:.jpg /.jpeg /.png The size of the image file should not exceed 10MB, the width and height of the image should be no less than 300px, and the aspect ratio of the image should be between 1:2.5 and 2.5:1 | |
| sound | boolean | No | true | - | Whether sound is generated simultaneously when generating a video |
| duration | integer | No | 5 | 5, 10 | The duration of the generated media in seconds. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Array of URLs to the generated content (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.has_nsfw_contents | array | Array of boolean values indicating NSFW detection for each output |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |