Kling Lipsync Audio to Video | AI Digital Human API

Kling LipSync — Audio-to-Video Lip Synchronization

Kling LipSync is an advanced audio-to-video model that drives natural, lifelike lip movements to match any input audio. Give it a clean voice or singing track plus a video, and it reanimates the mouth region so your character looks like they are truly speaking or singing those lines.

What Kling LipSync does

Synchronizes lip movements in a video to match provided speech or singing.
Works perfectly with videos generated by Kling AI or other sources.
Preserves the original background, body motion, and camera work.
Produces realistic, production-ready talking or singing footage.

Key Features

Natural, highly matched lip motion Mouth shapes line up closely with phonemes in the audio, while respecting each character’s facial structure. This yields expressive, believable speech and singing instead of robotic mouth flapping.
Accurate facial muscle response Lip animation also drives cheeks, jawline, and surrounding muscles. Subtle stretches and contractions are reflected in real time, greatly improving realism and immersion.
Non-destructive background and body Only the face region is re-rendered. Clothing, hands, environment, and lighting outside the face stay consistent with the original video, preserving continuity and avoiding unwanted artifacts.

Inputs and Outputs

Required inputs

audio: The target voice or singing track (locally recorded or generated). Duration of this audio controls billing and should roughly match the video length.
video: The source video whose character(s) will be lip-synced to the audio.

Output

A new video where the character’s lip movements and facial micro-motions are synchronized with the provided audio while the rest of the frame remains unchanged.

Pricing

Billing is based on the audio duration with a 5-second minimum and a cap at 600 seconds.

From this:

Effective price per second: 0.15 / 5 = $0.03 per second
Minimum billed duration: 5 seconds → minimum charge $0.15
Maximum billed duration: 600 seconds → maximum charge $18.00

Summary table:

Metric	Value
Price per second	$0.030
Minimum billed duration	5 seconds
Minimum total price	$0.15
Maximum billed duration	600 seconds
Maximum total price per run	$18.00

Example costs:

Audio length	Billed seconds	Total price
4 s	5 s	$0.15
10 s	10 s	$0.30
60 s	60 s	$1.80
180 s	180 s	$5.40
600 s	600 s	$18.00
900 s	600 s (capped)	$18.00

How to Use

Upload or paste the URL of your audio track.
Upload or paste the URL of the video to be lip-synced.
Ensure the audio length is close to the video duration for best results.
Click Run.
Preview the output video, then download it for editing or publishing.

Tips for Best Quality

Use clean, high-quality audio without heavy background noise or music.
Keep the audio and video durations aligned; large mismatches can cause timing drift.
Choose videos with clear views of the speaker’s face and minimal occlusions.
Avoid extreme motion blur or rapid cuts during key speaking moments.

Note

Please note that the length of the input audio and video must be at least 2 seconds, otherwise a compilation error will occur.

Kling Lipsync Audio To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/kwaivgi/kling-lipsync/audio-to-video with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Kling Lipsync Audio To Video below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-lipsync/audio-to-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "audio": "https://example.com/your-audio.mp3",
    "video": "https://example.com/your-input.mp4"
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("kwaivgi/kling-lipsync/audio-to-video", {
        "audio": "https://example.com/your-audio.mp3",
        "video": "https://example.com/your-input.mp4"
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "kwaivgi/kling-lipsync/audio-to-video",
    {
    "audio": "https://example.com/your-audio.mp3",
    "video": "https://example.com/your-input.mp4"
}
)

print(output["outputs"][0])  # → URL of the generated output

Kling Lipsync Audio To Video API — Frequently asked questions

What is the Kling Lipsync Audio To Video API?

Kling Lipsync Audio To Video is a Kuaishou model for talking-avatar generation, exposed as a REST API on WaveSpeedAI. Kling LipSync converts audio into talking head video by generating lifelike lip movements perfectly synced to the input audio. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Kling Lipsync Audio To Video API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-lipsync-audio-to-video.

How much does Kling Lipsync Audio To Video cost per run?

Kling Lipsync Audio To Video starts at $0.15 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Kling Lipsync Audio To Video accept?

Key inputs: `video`, `audio`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-lipsync-audio-to-video.

How long does Kling Lipsync Audio To Video take to generate?

Average end-to-end generation time on WaveSpeedAI is around 103 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Kling Lipsync Audio To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (Kuaishou). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

ExamplesView all

Related Models

README