APIMODELSAPIMODELS
All
Models/Kling AI Avatar
Kling

Kling AI Avatar (Kuaishou) API

kling-avatar

Kling AI Avatar turns one portrait and 2 to 300 seconds of speech or singing into a talking video, with lip movement and expressions that follow the audio and an optional prompt for actions and camera. Standard mode renders 720p at $0.062 per second of audio and Pro renders 1080p at $0.123, rounded up to the whole second. Failed generations are not charged.

Image + Audio to VideoLip Sync & ExpressionsPrompt-Guided Actions & CameraStandard 720p / Pro 1080pUp to 300sFrom $0.062/s of Audio
Standard 720p, per second of audio$0.062
Pro 1080p, per second of audio$0.123
Standard, 2s audio (minimum)$0.124
Standard, 10s audio$0.620
Pro, 10s audio$1.230
Standard, 60s audio$3.720
Pro, 60s audio$7.380
Standard, 300s audio (maximum)$18.600
Pro, 300s audio (maximum)$36.900
API Docs

Kling Avatar Talking Video

One clear face works best. JPG or PNG, up to 10 MB, shortest side at least 300 px, aspect ratio between 1:2.5 and 2.5:1.

Speech or singing, MP3, WAV, M4A or AAC, 2-300 seconds, up to 5 MB. The video runs as long as this audio.

or paste a public audio URL

Standard $0.062/s of audio, Pro $0.123/s. Pro gives a sharper 1080p video.

0/2500

Billed per second of audio, rounded up to the whole second: 2 s minimum ($0.124), 300 s maximum ($18.60). Failed generations are not charged.

Calling it from code? See the API docs.

Result

Your Kling Avatar video will appear here

Photo + Voice to Talking Video

One portrait and one driving audio clip become an MP4 in which the person says or sings it, with lip movement and expressions that follow the sound

Up to 5 Minutes per Video

Driving audio from 2 to 300 seconds in MP3, WAV, M4A or AAC; the video runs as long as the audio

Prompt-Guided Actions

An optional prompt of up to 2,500 characters describes actions, emotion and camera movement while the audio keeps the timing

Standard 720p or Pro 1080p

mode std renders 720p at $0.062 per audio second; mode pro renders 1080p at $0.123 for a sharper result

Only Success Is Charged

Failed generations are not charged, and audio we cannot measure or that falls outside 2-300 seconds is rejected with a 400 before a task is created

Billed by the Audio Second

Rounded up to the whole second: a 3.53-second clip bills 4 seconds ($0.248 standard); 60 seconds is $3.72 standard or $7.38 pro

TL;DR Kling AI Avatar is a Kling video generation model, callable via APIMODELS' unified API (model name `kling-avatar`). Pricing: Standard 720p, per second of audio: $0.062, Pro 1080p, per second of audio: $0.123, Standard, 2s audio (minimum): $0.124, Standard, 10s audio: $0.62, Pro, 10s audio: $1.23, Standard, 60s audio: $3.72, Pro, 60s audio: $7.38, Standard, 300s audio (maximum): $18.6, Pro, 300s audio (maximum): $36.9. One API key for all image / video / LLM / audio models.

About Kling AI Avatar

Kling AI Avatar is a Video Generation API provided by Kling. Kling AI Avatar is the talking-avatar model in Kuaishou's Kling API: give it one portrait and one driving audio clip, and it returns an MP4 in which that person says or sings the audio, with lip movement and facial expressions that follow the sound. On APIMODELS it is one model id, kling-avatar (kling-ai-avatar also works), on the unified video endpoint. Send the portrait as image_url and the audio as audio_url, each as a public URL or a base64 data URI. The portrait must be JPG or PNG, up to 10 MB, with the shorter side at least 300 pixels and an aspect ratio between 1:2.5 and 2.5:1; the audio can be MP3, WAV, M4A or AAC, 2 to 300 seconds long and up to 5 MB. An optional prompt of up to 2,500 characters describes actions, emotion and camera movement, while the audio keeps the timing. mode chooses the quality: std renders 720p and pro renders 1080p (resolution 720p or 1080p is accepted too). The video runs as long as the audio: in our test on 21 November 2026, a 3.53-second voice clip and a 1280x720 portrait in standard mode returned a 3.47-second video after 146 seconds. Billing is per second of driving audio, rounded up to the whole second and measured when the task is created: $0.062 per second in standard mode and $0.123 in pro mode, so the 3.53-second clip bills 4 seconds, $0.248 in standard. The minimum is 2 seconds ($0.124 standard, $0.246 pro) and the maximum 300 seconds ($18.60 standard, $36.90 pro). Audio whose length cannot be read, or that falls outside 2 to 300 seconds, is 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: Standard 720p, per second of audio: $0.062, Pro 1080p, per second of audio: $0.123, Standard, 2s audio (minimum): $0.124, Standard, 10s audio: $0.62, Pro, 10s audio: $1.23, Standard, 60s audio: $3.72, Pro, 60s audio: $7.38, Standard, 300s audio (maximum): $18.6, Pro, 300s audio (maximum): $36.9.

Related model: OmniHuman 2.0 — ByteDance's photo + audio model — 4-300 seconds, gestures and singing, $0.091 per audio second

Related model: Kling AI Lip Sync — when you already have a video and only want new speech on it — $0.077 per 5 seconds of video

Related model: Digital Human — when you have footage of the person and want to keep its original motion — $0.01 per audio second

Key Features

  • Photo + Voice to Talking Video -- One portrait and one driving audio clip become an MP4 in which the person says or sings it, with lip movement and expressions that follow the sound
  • Up to 5 Minutes per Video -- Driving audio from 2 to 300 seconds in MP3, WAV, M4A or AAC; the video runs as long as the audio
  • Prompt-Guided Actions -- An optional prompt of up to 2,500 characters describes actions, emotion and camera movement while the audio keeps the timing
  • Standard 720p or Pro 1080p -- mode std renders 720p at $0.062 per audio second; mode pro renders 1080p at $0.123 for a sharper result
  • Only Success Is Charged -- Failed generations are not charged, and audio we cannot measure or that falls outside 2-300 seconds is rejected with a 400 before a task is created
  • Billed by the Audio Second -- Rounded up to the whole second: a 3.53-second clip bills 4 seconds ($0.248 standard); 60 seconds is $3.72 standard or $7.38 pro

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 Avatar 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 Avatar API cost?

Billing is per second of driving audio, rounded up to the whole second and measured when the task is created: $0.062 per second in standard mode (720p) and $0.123 in pro mode (1080p). A 3.53-second clip bills 4 seconds, $0.248 in standard; 60 seconds is $3.72 standard or $7.38 pro. Failed generations are not charged.

What image and audio does Kling AI Avatar accept?

One portrait in JPG or PNG, up to 10 MB, with the shorter side at least 300 pixels and an aspect ratio between 1:2.5 and 2.5:1, plus one driving audio clip in MP3, WAV, M4A or AAC, 2 to 300 seconds and up to 5 MB. Both can be public URLs or base64 data URIs. Audio we cannot measure, or outside 2-300 seconds, is rejected with a 400 before anything is charged.

How long is the Kling AI Avatar video, and what does mode change?

The video runs as long as the driving audio. mode std renders 720p and mode pro renders 1080p at about twice the price. In our test on 21 November 2026, 3.53 seconds of speech in standard mode returned a 3.47-second video after 146 seconds; that is one measurement, not a promise.

How do I call the Kling AI Avatar API?

Create an API key at apimodels.app, then POST to https://api.apimodels.app/v1/video/generations with model kling-avatar, image_url, audio_url and optionally prompt and mode. The response is a task id; poll GET /v1/video/generations?task_id= until the state is completed and read the MP4 from resultUrls[0], or pass callback_url to be notified.

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

On APIMODELS, Kling AI Avatar runs alongside 60+ models on one API key and one balance, so choosing is about fit, not lock-in. It supports Image + Audio to Video, Lip Sync & Expressions, Prompt-Guided Actions & Camera, Standard 720p / Pro 1080p, Up to 300s, From $0.062/s of Audio, 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 Avatar do?

Kling AI Avatar supports: Image + Audio to Video, Lip Sync & Expressions, Prompt-Guided Actions & Camera, Standard 720p / Pro 1080p, Up to 300s, From $0.062/s of Audio. See the APIMODELS docs for full parameters and call examples.

Can I use the Kling AI Avatar 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 Avatar 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