APIMODELSAPIMODELS
All
Models/Kling AI Lip Sync
Kling

Kling AI Lip Sync (Kuaishou) API

kling-lip-sync

Kling AI Lip Sync re-voices an existing video: send a 2-60 second video with a clear face and a new audio clip, and the same video comes back with that face speaking the new audio. Face detection runs inside the same request, face_index picks the speaker, and the price is $0.077 per started 5 seconds of the input video. Failed generations are not charged.

Video + New AudioFace Detection IncludedPick the Speaker by face_indexTrim & Place the Audio2-60s at 720p / 1080p$0.077 per 5s of Video
per started 5 seconds of input video$0.077
5s video$0.077
10s video$0.154
30s video$0.462
60s video (maximum)$0.924
API Docs

Kling Lip Sync

The face that should speak must be visible for at least 2 seconds. The output keeps the video length.

MP3, WAV, M4A or AAC, 2-60 seconds, up to 5 MB.

or paste a public audio URL

Billed per started 5 seconds of the input video, whatever the audio length; face detection is included. A 6-second video is $0.154, a 60-second video $0.924. Failed generations are not charged.

Calling it from code? See the API docs.

Result

Your lip-synced video will appear here

Re-voice an Existing Video

Send a video and a new audio clip; the same video comes back with the chosen face speaking the new audio

One Request, Face Detection Included

We run Kling's face detection and the lip-sync job in one call; face_index picks the speaker when several people are on screen

Trim and Place the Audio

audio_start_ms and audio_end_ms trim the clip, insert_at_ms sets where it starts, and two volume controls balance it against the original sound

2-60 Second Videos

MP4 or MOV at 720p or 1080p, up to 100 MB; the output keeps the input length

Only Success Is Charged

Failed generations are not charged, and files we cannot measure or that fall outside 2-60 seconds are rejected with a 400 before a task is created

$0.077 per 5 Seconds of Video

Billed on the input video, not the audio, per started 5 seconds: 6 seconds is $0.154 and 60 seconds is $0.924

TL;DR Kling AI Lip Sync is a Kling video generation model, callable via APIMODELS' unified API (model name `kling-lip-sync`). Pricing: per started 5 seconds of input video: $0.077, 5s video: $0.077, 10s video: $0.154, 30s video: $0.462, 60s video (maximum): $0.924. One API key for all image / video / LLM / audio models.

About Kling AI Lip Sync

Kling AI Lip Sync is a Video Generation API provided by Kling. Kling AI Lip Sync is the lip-sync model in Kuaishou's Kling API: give it a video with a person on screen and a new audio clip, and it returns the same video with that person's lips moving to the new audio. On APIMODELS it is one model id, kling-lip-sync (kling-lipsync and kling-advanced-lip-sync also work), on the unified video endpoint, and it is a single request: we run Kling's face detection and the lip-sync job for you. Send the video as video_url and the new speech as audio_url. The video must be MP4 or MOV, 2 to 60 seconds, 720p or 1080p with both sides between 512 and 2160 pixels, up to 100 MB; the audio can be MP3, WAV, M4A or AAC, 2 to 60 seconds, up to 5 MB. One person is lip-synced per request: face_index picks which detected face (0, the default, is the first), and the chosen face has to be on screen for at least 2 seconds while the audio plays. Optional audio_start_ms and audio_end_ms trim the audio (the kept part must be at least 2 seconds), insert_at_ms sets where it starts in the video (by default, when the chosen face first appears), and audio_volume and original_audio_volume (0 to 2, default 1) balance the new voice against the video's own sound. The output keeps the input video's length: in our test on 21 November 2026, a 6.0-second 720p video with a 3.5-second voice clip came back as a 5.97-second video after 111 seconds. Billing follows the input video, not the audio: $0.077 per started 5 seconds, measured when the task is created, with face detection included, so 5 seconds costs $0.077, 6 or 10 seconds $0.154 and 60 seconds $0.924. Videos or audio whose length cannot be read, or that fall outside 2 to 60 seconds, are rejected with a 400 before anything is charged, and failed generations are not charged. Through APIMODELS platform, you can access this model via a unified API with transparent pay-as-you-go pricing. Current pricing: per started 5 seconds of input video: $0.077, 5s video: $0.077, 10s video: $0.154, 30s video: $0.462, 60s video (maximum): $0.924.

Related model: Kling AI Avatar — when you only have a photo — animates a still portrait from the audio, up to 300 seconds, from $0.062 per audio second

Related model: Digital Human — another way to re-sync the mouth on existing footage, billed per audio second at $0.01

Related model: OmniHuman 2.0 — when the person should also gesture or sing from a single photo — 4-300 seconds, $0.091 per audio second

Key Features

  • Re-voice an Existing Video -- Send a video and a new audio clip; the same video comes back with the chosen face speaking the new audio
  • One Request, Face Detection Included -- We run Kling's face detection and the lip-sync job in one call; face_index picks the speaker when several people are on screen
  • Trim and Place the Audio -- audio_start_ms and audio_end_ms trim the clip, insert_at_ms sets where it starts, and two volume controls balance it against the original sound
  • 2-60 Second Videos -- MP4 or MOV at 720p or 1080p, up to 100 MB; the output keeps the input length
  • Only Success Is Charged -- Failed generations are not charged, and files we cannot measure or that fall outside 2-60 seconds are rejected with a 400 before a task is created
  • $0.077 per 5 Seconds of Video -- Billed on the input video, not the audio, per started 5 seconds: 6 seconds is $0.154 and 60 seconds is $0.924

Use Cases

Marketing Videos

Quickly generate brand promotion videos for ad campaigns and social media marketing.

Social Media Content

Create compelling short-form video content for platforms like TikTok, Instagram, and YouTube.

Product Demos

Generate product feature demonstrations and tutorials to improve user conversion.

Educational Content

Produce course explanations, knowledge explainers, and training videos at an affordable price.

Why APIMODELS

  • Unified API -- One API key to access all models, no need to register on multiple platforms
  • Transparent Pricing -- Pay-as-you-go with per-call pricing published on every model page, ideal for indie developers and startups
  • Instant Access -- Start right after signup; pay by card, PayPal, Alipay or USDT
  • Full Documentation -- Detailed API docs with code examples in cURL, Python, and Node.js

Frequently Asked Questions

What is the difference between APIMODELS and the official Kling API?

APIMODELS offers the same Kling AI Lip Sync model through our aggregation platform. We provide a unified API interface so you do not need separate accounts for each provider - one API key to access all models.

How much does the Kling AI Lip Sync API cost?

$0.077 per started 5 seconds of the input video, measured when the task is created. The audio length does not change the price, and face detection is included. 5 seconds costs $0.077, 6 or 10 seconds $0.154 and 60 seconds $0.924. Failed generations are not charged.

What video and audio does Kling AI Lip Sync accept?

A video in MP4 or MOV, 2 to 60 seconds, 720p or 1080p with both sides between 512 and 2160 pixels, up to 100 MB, and a new audio clip in MP3, WAV, M4A or AAC, 2 to 60 seconds, up to 5 MB. The face to lip-sync has to be on screen for at least 2 seconds while the audio plays. Files we cannot measure, or outside 2-60 seconds, are rejected with a 400 before anything is charged.

Can Kling AI Lip Sync handle several people in one video?

One person is lip-synced per request. face_index picks which detected face to use (0, the default, is the first face Kling finds); to re-voice two people, send two requests. insert_at_ms sets where the audio starts, by default when the chosen face first appears.

How do I call the Kling AI Lip Sync API?

Create an API key at apimodels.app, then POST to https://api.apimodels.app/v1/video/generations with model kling-lip-sync, video_url and audio_url, plus any of face_index, audio_start_ms, audio_end_ms, insert_at_ms, audio_volume and original_audio_volume. It is one request; face detection runs inside it. Poll GET /v1/video/generations?task_id= until completed and read the MP4 from resultUrls[0].

How does Kling AI Lip Sync compare with other models in the Video Generation category?

On APIMODELS, Kling AI Lip Sync runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Video + New Audio, Face Detection Included, Pick the Speaker by face_index, Trim & Place the Audio, 2-60s at 720p / 1080p, $0.077 per 5s of Video, and you can weigh it on price and capability against other models in the Video Generation category, then switch by changing a single model-name string — no new account or integration. Browse every model in that category with live pricing at apimodels.app/models.

What can Kling AI Lip Sync do?

Kling AI Lip Sync supports: Video + New Audio, Face Detection Included, Pick the Speaker by face_index, Trim & Place the Audio, 2-60s at 720p / 1080p, $0.077 per 5s of Video. See the APIMODELS docs for full parameters and call examples.

Can I use the Kling AI Lip Sync API from any country, including mainland China?

Yes. APIMODELS does not restrict access by country: the site and the API answer requests from anywhere, and apimodels.app and api.apimodels.app are reachable directly from mainland China without a proxy. You call Kling AI Lip Sync with one APIMODELS key, so you do not need a separate account with the model's developer.

What payment methods are supported? Can I pay with PayPal or crypto?

Yes to both. You can top up with a card (Visa, Mastercard and others, through Stripe), PayPal, Alipay, or USDT on TRON (TRC20) or BNB Smart Chain (BEP20). Card, PayPal and Alipay top-ups are credited immediately; USDT is credited once the transfer confirms on-chain. Auto top-up is optional, and a $50 top-up adds a $1 bonus ($3 on a $100 top-up). The balance is in USD and billed per use, with no subscription.

Related models