California-based startup MyShell, in collaboration with MIT and Tsinghua University, has unveiled a groundbreaking open-source AI named OpenVoice, offering unparalleled speed and accuracy in voice cloning.OpenVoice sets itself apart by requiring just seconds of audio to replicate a voice, providing users with detailed control over tone, emotion, accent, rhythm, and more. Developed by combining two AI models, the system excels in text-to-speech conversion and voice tone cloning, promising a swift and efficient voice replication process.

MyShell's innovative creation was introduced this week through a post, accompanied by a pre-reviewed research paper detailing the technology. Users can experience the capabilities of OpenVoice through demo sites on MyShell and HuggingFace. With $5.6 million in early funding and a substantial user base, MyShell positions itself as a decentralized platform for AI app creation and discovery, not only excelling in instant voice cloning but also offering a diverse range of text-based chatbot personalities, meme generators, user-created text RPGs, and more. By open-sourcing its voice cloning capabilities and simultaneously monetizing its broader app ecosystem, MyShell aims to promote an open model of AI development while expanding its user base across various applications.