UniRouteUniRoute
All models
Kling 2.6
Video

Kling

Kling 2.6

Use the Kling 2.6 API to generate complete audio-visual videos from text or images. Create outputs with synchronized speech, ambient sound, and motion timing, and run a quick test in the UniRoute Playground before using the API.

Pricing

TierUniRouteMarket
text-to-video · without audio-5.0s$0.275$0.35
image-to-video · without audio-5.0s$0.275$0.35
text-to-video · without audio-10.0s$0.55$0.70
text-to-video · with audio-5.0s$0.55$0.70
image-to-video · without audio-10.0s$0.55$0.70

per video

About this model

Kling 2.6 API on UniRoute supports text-to-audio-visual generation from a single sentence. Users input text, and the model produces video with voice, sound effects, and ambient layers. This workflow provides an efficient way to create structured audio-visual output from written prompts.

Text-to-videoImage-to-video

Deep dive

Text-to-Audio-Visual Generation with Kling 2.6 API

Kling 2.6 API on UniRoute supports text-to-audio-visual generation from a single sentence. Users input text, and the model produces video with voice, sound effects, and ambient layers. This workflow provides an efficient way to create structured audio-visual output from written prompts.

Image-to-Audio-Visual Workflow Using Kling Video 2.6 API

Kling Video 2.6 API converts static images into audio-visual content. Users upload an image or combine it with text, and the model generates video with speech, sound effects, and ambient sound. This workflow supports transforming existing images into dynamic, audio-enhanced sequences.

Call it with one request

Works with the OpenAI SDK — just change the base URL.

api.uniroute.dev
curl https://api.uniroute.dev/v1/video/generations \
  -H "Authorization: Bearer $UNIROUTE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kling-2-6",
    "prompt": "Drone shot over a neon city at night",
    "duration": 8
  }'

Related models