Kuaishou (Kling) · Text to Audio

Kling Audio

Kling Audio Text To Audio is available in the Business API catalog.

text → audio
kling/kling-audio/text-to-audio

Examples

representative generations · starting points to seed the playground

Dense tropical rainforest at dawn, layered birdsong far and near, dripping leaves, insect hum, no music, loop-friendly.

Open in playground

Bustling Shibuya crossing at night: layered crowd footsteps, distant traffic, pachinko chimes, city buzz, no music.

Open in playground

Cozy crackling fireplace, soft wind outside a cabin, occasional wood pops, warm intimate room tone, no music.

Open in playground

Underwater coral reef ambience: bubbling, distant whale song, gentle current, muffled aquatic tones, no music.

Open in playground

Medieval tavern interior: murmuring crowd, clinking tankards, a soft lute melody, crackling hearth, wooden creaks.

Open in playground

Haunted-house horror ambience: groaning floorboards, a distant slamming door, cold wind through broken windows, faint whispers, a dragging chain, distant thunder.

Open in playground

Per-model pricing

Transparent, usage-based rates for every Kuaishou (Kling) model.

Kling Lipsync

$0.012 / sec
Avatar

Kling Audio

Current
$0.028 / request
Text to Audio

Kling Audio

$0.028 / request
Video to Audio

Kling AI Avatar v2

from $0.045 / sec
Avatar

Kling 3.0 (Text to Video)

from $0.068 / sec
Text to Video

Kling 3.0 (Image to Video)

from $0.068 / sec
Image to Video

Kling 3.0 (Omni Video)

from $0.068 / sec
omni-video

Kling 3.0 Turbo (Text to Video)

from $0.09 / sec
Text to Video

Kling 3.0 Turbo (Image to Video)

from $0.09 / sec
Image to Video

Kling 3.0 (Motion Control)

from $0.101 / sec
Motion Control