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 img_uuid, then poll or receive callback updates until the task reaches a terminal state.
Get API Key
Cinematic landscape representing Kling 2.6 API video generation

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.
Handcrafted miniature landscape for prompt-driven video generation

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.
Continuous cinematic corridor representing frame-guided motion and audio
Keep incompatible frame and audio options out of the same request.

Kling 2.6 API capabilities and validation rules

Model and prompt

Set model to kling-2-6. A prompt is required and accepts up to 2,500 characters.

Input frames

Use image_url for a first frame. Optional image_end_url 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; quality 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 voice_ids require an input image and audio enabled; use @1 and @2 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.
Get API Key
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.

Kling 2.6 API FAQ

What endpoint does the Kling 2.6 API use?

Send a POST request to https://api.goenhance.ai/api/v1/videos/generations with model set to kling-2-6. A successful submission returns data.img_uuid.

What is the Kling 2.6 API pricing?

Without audio, pricing is 2.1 tokens/s ($0.042/s) at 720p and 3.5 tokens/s ($0.07/s) at 1080p. At 1080p, native audio is 7 tokens/s ($0.14/s), or 8.4 tokens/s ($0.168/s) with designated voices.

Can I combine a last frame with native audio?

No. A first-and-last-frame request forces 720p, while native audio requires 1080p. Remove image_end_url or disable audio.

How do designated voices work?

Supply up to two voice_ids with an input image and generate_audio: true. Their order maps to @1 and @2 in the prompt. A single voice_id alias is also accepted.

Which duration, resolution, and ratio values are supported?

Duration accepts 5 or 10 seconds. Resolution accepts 720p or 1080p. Text-to-video ratios are 16:9, 9:16, and 1:1; image-guided requests use the input image's ratio.

How do callbacks work?

Provide a public HTTPS callback URL. GoEnhance sends job-detail-shaped updates for processing, success, and failure; non-200 responses are retried up to three times with a three-second timeout per attempt.

Is this Kuaishou's official API?

No. This page describes independent access to Kling 2.6 through GoEnhance. GoEnhance is not presented as Kuaishou or Kling's official API, partner, or model developer.

Start building with the Kling 2.6 API