Kling AI Avatar Pro is Rivya's higher-fidelity AI talking avatar model for turning one portrait image and one audio clip into a more polished presenter video.
The final cost is rounded up to whole credits.

Example output
Kling AI Avatar Pro
Lip-Synced Avatar · Image + Audio Driven

Example output
Kling AI Avatar Pro
Best for
Supports
Try this model
No results to display yet.
Model examples
Review examples to help decide whether the model fits your task.
Model strengths
Model strengths
Suggested uses
Tasks to consider
Model details
Provider
Kuaishou
Category
Video
Capabilities
Lip-Synced Avatar · Image + Audio Driven
Credit charges
Credit rate: 16 per second of input
Inputs
1 image + 1 audio file
Prompt requirements
Optional prompt
Developer access
Kling AI Avatar Pro can be called through Public API v1. Modes that use reference media require uploads through the Files API. Check the model reference for supported inputs.
Kling AI Avatar Pro FAQ
Kling AI Avatar Pro is strongest when the job needs a cleaner, more polished presenter-style talking avatar from one portrait and one audio clip. It fits branded presenter videos, premium explainers, and higher-finish avatar shorts when that extra quality justifies the 16-credit-per-second rate.
On Rivya, this option is built around one portrait image, one audio clip of up to 300 seconds, and an optional prompt. It costs 16 credits per second of verified audio, and the total is rounded up to a whole credit.
The biggest decision is usually whether the source portrait and source audio are already polished enough to deserve the Pro tier. Because the public page setup is intentionally simple here, most of the result quality comes from the face-forward image, the clarity of the audio, and whether the extra polish is worth paying for versus the cheaper Standard tier.
Rivya charges 16 credits per second of verified audio, up to 300 seconds, with the total rounded up to a whole credit. The Pro rate is easiest to justify when a higher-fidelity branded presenter or explainer clip matters more than the lowest-cost avatar pass.
Choose Kling AI Avatar Standard when its lower 8-credit-per-second rate is enough. Choose Kling AI Avatar Pro when you still want the simple portrait-plus-audio project, but the result needs to look more premium at 16 credits per second. Both tiers are billed from verified audio duration, up to 300 seconds.
Start here when the first result needs to tell you whether one portrait and one audio clip can already produce a polished presenter-style avatar video. Use it for premium explainer clips and branded short-form delivery where quality matters more than keeping the first avatar pass as inexpensive as possible.
This page is a portrait-plus-audio avatar option with an optional prompt. It is billed at 16 credits per second of verified audio, up to 300 seconds, so the first result is mainly about validating one face-forward image and one final audio track.
Before you run, make sure the portrait is clean and front-facing, the audio is the take you actually want to keep, and the optional prompt only adds light tone or scene guidance. On this model, source quality does more than parameter tweaking because the public control setup is intentionally minimal.
The page is public, but the actual first image-led video run is still gated behind sign in. Rivya charges 16 credits per second of verified audio, with a 300-second maximum and the total rounded up, so you can line up the portrait, audio, and tone direction before signing in to generate.
Stay on this page while you are checking one portrait-audio pair and checking whether the Pro pass is worth keeping. Open the full Studio once the work needs saved versions, multiple avatar assets, or a longer production thread around the same presenter or character.
Compare alternatives
Create Seedance 2.5 videos from text, a start frame with an optional end frame, or image, video, and audio references. Choose 480p, 720p, or 1080p, a duration from 4 to 30 seconds or automatic duration, and an MP4 or MOV format request.
Why consider it
Input option: Up to 50 reference files
Generate video from text, a first frame, or media references.
Why consider it
Input option: Prompt, first frame with optional last frame, or image/video/audio references
ByteDance's Seedance 2.0 Fast video model for text prompts, a first frame with an optional last frame, or image, video and audio references. Choose 480p or 720p, set a 4–15-second duration, and request audio or a returned last frame.
Why consider it
Input option: Prompt, first frame with optional last frame, or image/video/audio references