AI Voice Cloning of Genshin Impact Characters Surpasses 1.36 Million Views
-
Recently, Bilibili UP主 'Xiao Chong Ge_' released a fan-made Genshin Impact video where characters imitate Furina's lines and movements while retaining their original voices, leaving netizens utterly amazed. As of the time of writing, the video has garnered over 1.36 million views.
Many Genshin Impact players were drawn to the 'unfamiliar familiarity' of seeing familiar characters mimic another character's lines and actions, prompting numerous netizens to tag their friends in the comments, exclaiming, 'I can't be the only one traumatized by this.'
A netizen raised questions about actions and modeling in the comments, with someone asking, 'What's up with the ultimate move voice?'. According to UP owner 'Xiaochong Ge_', he utilized the VITS voice synthesis model to mimic the voice tones of various Genshin Impact characters.
The principle of this model involves uploading voice text, which is then analyzed to extract language features. These features are passed to an acoustic model, which analyzes the acoustic characteristics. Finally, these features are sent to a vocoder, which generates the corresponding sound waves. Simply put, the acoustic model preserves the unique vocal characteristics of each character in Genshin Impact. Without considering the technical background, by 'providing a voice' to the VITS model, anyone can create their own personalized 'voice library' at a low cost.
<p class="article-content__img" style="margin-top: 0px; margin-bottom: 28px; padding: 0px; box-sizing: border-box; outline: 0px; border-width: 0px; border-style: solid; border-color: rgb(229, 231, 235); --tw-shadow: 0 0 #0000; --tw-ring-inset: var(--tw-empty, ); --tw-ring-offset-width: 0px; --tw-ring-offset-color: #fff; --tw-ring-color: rgba(41, 110, 228, 0.5); --tw-ring-offset-shadow: 0 0 #0000; --tw-ring-shadow: 0 0 #0000; line-height: 32px; text-align: center; color: rgb(59, 59, 59); word-break: break-word; font-family: 'PingFang SC', 'Microsoft YaHei', Helvetica, 'Hiragino Sans GB', 'WenQuanYi Micro Hei', sans-serif; letter-spacing: 0.5px; display: flex; -webkit-box-align: center; align-items: center; -webkit-box-pack: center; justify-content: center; flex-direction: column; text-wrap: wrap; background-color: rgb(255, 255, 255);"><img src="https://www.cy211.cn/uploads/allimg/20231114/1-231114142141541.png" title="image.png" alt="image.png" style="margin: 0px auto; padding: 0px; box-sizing: border-box; outline: 0px; border: 1px solid rgb(238, 238, 238); --tw-shadow: 0 0 #0000; --tw-ring-inset: var(--tw-empty, ); --tw-ring-offset-width: 0px; --tw-ring-offset-color: #fff; --tw-ring-color: rgba(41, 110, 228, 0.5); --tw-ring-offset-shadow: 0 0 #0000; --tw-ring-shadow: 0 0 #0000; max-width: 700px; background: url('../img/bglogo2.svg') center center no-repeat rgb(247, 248, 249); box-shadow: rgba(27, 95, 160, 0.1) 0px 1px 3px; display: inline-block;"/></p>
AI voice cloning is no longer a new topic. Some AI voice tools like HeyGen and AI Dubbing offer free trials, lowering the barrier for ordinary users. With technological advancements, how to create unique and innovative works in terms of content and form may be the more pressing issue for creators to focus on now.
