Frequently Asked Questions
Avatar SDK allows users to automatically generate recognizable 3D avatars based on their photos. You can check MetaPerson Creator to try our technology on your photos.
The default way of using is integration of MetaPerson Creator into your applications. We provide ready sample projects for popular target platforms and detailed video tutorials.
Also, the product can be used as a cloud service or can be applied to compute avatars on the client’s side.
It is possible to get a free trial for one week on the website. To start a trial you will be asked to create an account and add a payment source.
A Pro subscription is necessary to integrate this into your product. If you're interested in creating full-body avatars using the REST API or looking for an offline solution, please reach out to us regarding our Enterprise plan.
See our pricing page for details.
We recommend learning avatar comparison on the website, choosing the needed avatar type, and then taking a trial for the Pro plan.
After getting a trial, we recommend starting with this page.
We recommend trying MetaPerson Creator to check our greatest avatars. If you want to try Avatar SDK on an Android phone, you can check our test application for Head avatars. Also, you can look at RemoteFace, our virtual camera for video conferencing that shows your avatar driven by camera and lipsync instead of the usual video feed.
Avatar SDK's flagship product is the MetaPerson avatars available on the Pro subscription and higher. It is a full-body game-ready avatar created from a single selfie. If you need only a head or a bust, you can use our Head avatars. See https://avatarsdk.com/avatars/ for more details.
Yes! MetaPerson avatars now support both realistic and cartoon-style. You can generate a stylized, animated version of yourself from a single selfie — perfect for games, digital content, and creative projects. We recommend trying MetaPerson Creator to check this feature.
You can see our pricing on the Pricing page. It is possible to cancel your subscription at any time in your profile or schedule your account cancellation during the trial on the billing page.
You can schedule your account cancellation on the billing page in your profile. Trial and general subscriptions can be canceled at any time and will remain active till the end of the current billing period. Our support will be happy to help you with subscription management, please send your request to support@avatarsdk.com from the email associated with your Avatar SDK account.
Yes, we have an offline solution of Avatar SDK. It is available on the Enterprise plan, you can send an inquiry by clicking the “Request a quote” on the Pricing page.
There are monthly quotas included in your subscription. Our billing system will charge you extra for the avatars created above the quota. You can check the details for a specific subscription plan on the Pricing page or in your Profile after registration.
By default, SDK generates the avatar in the maximum possible resolution. Almost all our pipelines also support several levels of detail. You can find more information here.
We support gltf, glb, fbx, obj, ply. However, not all of these formats are supported in all SDK modifications (REST API, Unity plugin, native library, etc) for all avatar pipelines.
You can find the newer versions of SDK and their documentation here
Yes. Avatar SDK LiveSpeak turns text into speech and generates precise phoneme timing mapped to facial blendshapes, so the avatar speaks with synchronized lip and facial motion in real time. Try the live demo or read the LiveSpeak documentation. LiveSpeak is included in the Pro plan.
For webcam-driven facial motion, see our Face Capture SDK.
Our avatars also remain compatible with third-party lipsync tools such as Oculus Lipsync and SALSA if you already use them, details here.
The MetaPerson Creator is optimized for both desktop and mobile and can be integrated on both types of platforms. Our REST API is very lightweight and works in all environments. If you are looking to compute Head avatars locally, Local Compute avatar generation currently works on Windows, Ubuntu, Android, and iOS.
Our flagship product is the full-body game-ready MetaPerson avatars. Pro subscription is required to integrate them into your project. Read more here.
If you need to attach our avatars to different bodies (like the seamless attachment of avatars to your body models with texture blending), please contact us at support@avatarsdk.com.
The Local Compute requires an internet connection to check if your account is allowed to generate avatars and to report the number of calculated avatars to our system without uploading images or any other data. We also have an offline solution of Avatar SDK. It is available on the Enterprise plan, you can send an inquiry by clicking the “Request a quote” on the Pricing page.
Yes. Avatar SDK LiveSpeak converts text to speech and drives the avatar's facial blendshapes from the generated phoneme timing, so you get synchronized speech and facial animation without assembling your own audio pipeline. It is included in the Pro plan, try the live demo.
For body motion, Avatar SDK Move generates animation from a plain-language prompt. Avatars are rigged and Mixamo-compatible, so third-party animation and lipsync tools (Oculus Lipsync, Speech Graphics, SALSA) work as well, see the lipsync tutorials.
Yes. Avatar SDK Move is an AI text-to-animation tool: describe a motion in plain language, for example "walk confidently" or "wave to the audience", and Move generates the animation for your avatar with no motion capture and no manual keyframing. Move is in beta inside MetaPerson Creator and free to try.
Avatars are rigged and Mixamo-compatible, so existing animation libraries and your own clips work as-is. For speech and facial animation, see Avatar SDK LiveSpeak.
Yes, it is possible for Head avatars. We have a special type of avatars (“static”) that do not contain internal meshes and can be 3d printed. You need to call Avatar SDK API to calculate these avatars with the "static" subtype. It will allow you to get the model almost ready for 3d printing.
In another way, you can also try to use any other pipelines or subtypes, but you should post-process these models to prepare them for 3d printing and remove unneeded parts. You can use any 3d editor for this task.
Face Capture SDK is a beta version now and it is applied only as a native SDK for Windows and iOS. If you want to get a trial send us a request to support@avatarsdk.com. Please note that Face Capture SDK is available only for Pro subscribers.
The MetaPerson avatars support a lot of customization options, you can check them out in the MetaPerson Creator. Some modifications are available through the REST API and they are documented here.
Yes, Avatar SDK provides a set of outfits for MetaPerson avatars. Each outfit consists of mesh, texture, body visibility mask, roughness, metalness, and normals map. You can check them out in the MetaPerson Creator
You can add such resources on your own with taking advantage of avatar fixed topology in the case of MetaPerson avatars. If you want Avatar SDK to take care of reshaping your assets for each avatar shape, you can import them into Avatar SDK. The details for such a project are available on request.
We have a set of artificial haircuts that are modified during the avatar computation process to match each particular avatar head geometry for the MetaPerson avatars.
Also, there is a generated haircut for each avatar. This haircut is unique and generated for each particular avatar based on the source image.
If you need our head avatars with your full-body model, we can create a custom pipeline for you. We will need to look at your body model to provide you with a timeline and costs for such a project.
Fixed topology means that heads have a constant number of vertices and the same indices for them. E.g. in the case of adding your own landmarks, you can find the required vertices on one model and use them as landmarks, because their index will be the same for all avatars.