img_uuid, then poll or receive callback updates until the task reaches a terminal state.Kling 2.6 API for Video and Native Audio Workflows
Access Kling 2.6 through GoEnhance for text-to-video, image-to-video, first-and-last-frame control, and optional native audio. Submit one asynchronous request, save the returned
Get API Key
Choose a valid Kling 2.6 request mode
Prompt-led text-to-video
POST to https://api.goenhance.ai/api/v1/videos/generations with model: kling-2-6 and a required prompt of up to 2,500 characters. Omit image_url for text-to-video and select 16:9, 9:16, or 1:1 through ratio.
Image guidance, audio, and voices
Add image_url for image-to-video. Native audio requires 1080p, while a first-and-last-frame request forces 720p; those two modes cannot be combined. Up to two designated voices can be used with an input image and generate_audio: true.
Keep incompatible frame and audio options out of the same request.
Kling 2.6 API capabilities and validation rules
Model and prompt
Set <code>model</code> to <code>kling-2-6</code>. A prompt is required and accepts up to 2,500 characters.
Input frames
Use <code>image_url</code> for a first frame. Optional <code>image_end_url</code> requires that first frame and forces 720p.
Duration
Choose 5 or 10 seconds. The documented default is 5 seconds.
Resolution
Choose 720p or 1080p. The endpoint has no 4K tier; <code>quality</code> is accepted as an alias.
Aspect ratio
Text-to-video accepts 16:9, 9:16, or 1:1. With a first-frame image, the image determines the ratio.
Audio and voices
Native audio requires 1080p. Up to two <code>voice_ids</code> require an input image and audio enabled; use <code>@1</code> and <code>@2</code> in the prompt.
Rates are per generated second; USD equivalents use the documented $0.02 per token conversion. Multiply the selected rate by 5 or 10 seconds.
Kling 2.6 API pricing
720p without native audio
2.1 tokens per generated second, equal to $0.042 per second.
1080p without native audio
3.5 tokens per generated second, equal to $0.07 per second.
1080p with native audio
7 tokens per generated second ($0.14/s), or 8.4 tokens per second ($0.168/s) when designated voices are used.
Integrate Kling 2.6 in six steps
1
1. Create an API key
Create a GoEnhance API key and send it in the Authorization header.
2
2. Select the input mode
Choose prompt-only, first-frame, first-and-last-frame, or first-frame with audio and optional voices.
3
3. Validate constraints
Check duration, resolution, ratio behavior, and the mutually exclusive two-frame and native-audio modes.
4
4. Submit the task
POST to
/api/v1/videos/generations and persist the returned img_uuid. 5
5. Track status
Poll
GET /api/v1/jobs/detail or provide a publicly accessible HTTPS custom_callback_url. 6
6. Handle terminal states
Process success and failure updates idempotently. Callback bodies match the job-detail response.
Build repeatable video workflows around explicit inputs and asynchronous completion.
Developer use cases for Kling 2.6
Campaign clip variants
Generate short prompt-led concepts for human review and downstream editing.
Product image animation
Animate an approved product still while your application controls assets, prompts, and review gates.
Localized voice-led scenes
Use up to two designated voices with image-guided 1080p requests when the application needs controlled speaker cues.
Answers to common pricing, input, audio, callback, and Kuaishou API questions.