AI & RoboticsNews

AI avatars of Chinese authors could soon narrate audiobooks

The Chinese search engine Sogou isn’t stopping at AI news anchors. The company has created “lifelike” avatars of two Chinese authors, and it plans to have them narrate audiobooks in video recordings. According to the BBC, Sogou used AI, text-to-speech technology and video clips from the China Online Literature+ conference to create avatars of authors Yue Guan and Bu Xin Tian Shang Diao Xian Bing.

While text-to-speech technology can quickly create new audiobooks, the BBC says consumers prefer audiobooks narrated by authors, actors or famous public figures. With AI avatars, Sogou might be able to combine text-to-speech with the likeness of celebrities to create the illusion that audiobooks are being read by real people.

Sogou’s AI news anchors have been on air since last fall, working for China’s state-run news agency Xinhua. While they were advertised as lifelike and based on some of Xinhua‘s human anchors, it’s still pretty obvious that you’re watching avatars whose voices, facial expressions and mouth movements are synthesized using deep learning techniques. It’s hard to say if its audiobook narrators will be any more realistic.


Author: Christine Fisher
Source: Engadget
Tags: ai, audiobook, AudioBooks, author, av, avatar, bu xin tian shang diao xian bing, literature, narrator, reader, recording, robots, sogou, tomorrow, uncanny valley, video, xinhua, yue guan


Related posts
AI & RoboticsNews

DeepSeek’s first reasoning model R1-Lite-Preview turns heads, beating OpenAI o1 performance

AI & RoboticsNews

Snowflake beats Databricks to integrating Claude 3.5 directly

AI & RoboticsNews

OpenScholar: The open-source A.I. that’s outperforming GPT-4o in scientific research

DefenseNews

US Army fires Precision Strike Missile in salvo shot for first time

Sign up for our Newsletter and
stay informed!