Tips for Creating A Custom AI Avatar January 24, 2025 19:15 Updated You can now create your very own custom AI avatar. Check the following tips and tricks to produce the best results. Consent Statement Creating your video for your AI avatar Processing your video for your AI avatar Custom AI avatars are offered across all plans at an additional cost. For steps on how to purchase and create your custom avatar, check out this link here. Consent Statement Before you create your custom AI avatar, consent must be given. Vyond requires a clear, verbal consent statement to be submitted as a separate video along with the training video. This measure is crucial for ethical considerations and compliance with data protection regulations. Instances where this consent statement is missing can lead to processing delays or the inability to create your AI clone. Please record the following statement at the beginning of your video for your AI avatar: “My name is [full name]. By recording this video, I give Vyond permission to use my audio and video samples to create a digital avatar of me. I understand that this avatar can be shared within my team and used to create videos on my behalf.” Replace [FULL NAME] with your name. The statement must be clearly audible and understandable. We currently accept consent statements in any of the supported languages listed here. MP4 format is required. Vyond can accept resolutions 720p (minimum) up to 4K and a size limit of 750 MB. Ensure lens is free of smudges. For iPhone users, please do not use HDR as it will impact the results. Your Custom Avatar request can not be processed if the required consent statement is missing, incomplete, or does not meet the standards or requirements, and your digital avatar will be delayed. If you are notified of this issue, please: Re-Record Your Video: Record a new video saying the correct consent statement clearly Re-submit Your Video: On the avatar page, you will see an error in creating your avatar. Click on the error message and follow the steps to re-submit your video. Creating your video for your AI avatar Video recordings must be 2 minutes and under. The following tips can help create a more authentic and engaging digital representation for your AI avatar. Camera and Placement High quality camera with 2K pixels. For smartphone cameras, HDR must be turned off to prevent discoloration. Optimal FPS is 30, but 24-60 FPS is acceptable. Maintain a distance of 3ft-6ft (or 0.9m-1.8m) from the camera. The camera should be at eye level. Horizontal and vertical orientation are accepted. Note that your recorded orientation will also be your final Avatar orientation. For horizontal templates, please record your video in 16:9 ratio (for smartphones, this is landscape). Microphone Start with your phone or computer microphone. For external USB or XLR mics, ensure they are placed 1ft from your mouth, not exceeding 3ft. Position any external mic 1 inch below your mouth to prevent blocking the mouth. For best results, disable any software based audio enhancements. Turn off compressors, equalizers, and noise suppression as we perform our own sound processing post-recording. Recording Format MP4 format is required with a resolution of 720p (minimum) up to 4K (maximum) and a size limit of 750 MB. Vyond accepts up to 4K for resolution for AI avatars only. Common webcam resolutions (such as 720p/1080p) are also known to produce excellent avatars. For more genuine results, provide unedited raw footage. Lighting Ensure your face is evenly lit with no shadows. A large diffuse light can work best to provide even lighting for the entire face. Noise Your space should be silent or almost silent. Avoid noise from air conditioning, construction, traffic, refrigerators, and conversations. Choose rooms with minimal reverb to prevent sound amplification. Clean audio, free from background noises, will produce the best audio output for your avatar. Background Keep your background clear. A clean and simple background works best. Remove moving objects. Ensure no other people are visible in the video. Though you can move around in your video, for best results, it’s best to stay still. Dialogue Be yourself and relax. Speak at a natural pace and tone, but not monotone. Some expressiveness is good! Think as if you're talking to a friend. Be sure to briefly pause after each sentence (short, natural pauses). Close your lips during pauses (a script can help remind you). For your main avatar, keep an upbeat tone. The content should be positive and engaging. Speak in the language you are most likely to use for the generated videos. This does not prohibit future videos from being created in a different language if desired (30+ languages)! Keep continuous eye contact with the camera. Be animated in your mouth, eyes, and cheeks. If you stumble, continue naturally and keep speaking. A script is not needed but can be helpful. Time your script to ensure your video recording is 2 minutes and under. Use your natural speaking style. Facial Expressions Keep eye level with the camera and maintain eye contact. Keep a natural facial expression aligned with the topic you're speaking about. Avoid blocking your face and keep hand gestures to a minimum. Minimize overly expressive head motions. Note: Currently only one emotion can be attributed each recording (e.g. You can not have both angry and happy in the same recording or avatar at this time). Framing Eye contact should be just below the camera. Ideally position yourself 3 feet from the camera. We recommend recording yourself from the waist up to ensure our model detects the mouth movements. Keep hair strands away from your face. Your face should be facing the camera, not to the sides. Accessories and Beards Glasses and facial hair (beards and mustaches) should be ok but can produce mixed results on rare occasions. Processing your video for your AI avatar Once your consent statement is verified and your video has been submitted, your avatar will be processed and completed in approximately 4-6 hours. Related articles Custom AI Avatars AI Avatars Download and Generate Text to Speech Audio Consent and Sharing Permissions for Custom AI Avatars Custom AI Avatar Supported Languages