synthesia 4亿美元的头像技术允许用户创建交互式数字分身
synthesia是一家价值4亿美元的数字头像初创公司，现在允许用户创建基于特定文章或脚本的交互式数字分身，由语音转文本、语言和文本转语音模型提供支持。
synthesia, a digital avatar startup valued at $4 billion, has introduced a new product that enables users to create interactive digital twins. the process involves capturing photos and a voice recording, which are then used to train the digital twin. the digital twin can be powered by synthesia's own video and voice models or alternatives from other labs like cartesia, elevenlabs, google, or openai. the technology stack includes voice-to-text, agentic language, text-to-voice, and video models. synthesia's platform allows enterprises to build interactive training videos and roleplay sessions with ai avatars.