From Wikipedia, the free encyclopedia
Jump to: navigation, search

NeoSpeech is a company that specializes in Text-To-Speech (TTS) software for embedded devices, mobile, desktop, and network/server applications. NeoSpeech was originally founded by two speech engineers in Fremont, California in 2002. NeoSpeech is privately held, headquartered in Santa Clara, California. NeoSpeech created the Text2Speech Blog.[1]

Stephen Hawking is a well-known Neospeech TTS user.[2] Adobe Systems has selected Neospeech Speech synthesis for their elearning authoring suite called Adobe Captivate.[3]


VoiceText speech synthesis is the NeoSpeech software component that generates synthesized voice from a given input text, essentially turning text into speech. NeoSpeech uses Unit Selection Synthesis (USS), which utilizes large databases of recorded sound segments to create synthesized speech. The VoiceText TTS Engine is mainly used to build custom stand-alone TTS applications such as AAC (Augmentative and alternative communication) products,[4][5][6] gaming software, automated loud speaker/paging systems, educational software,[7] and language learning apps.[8] It also can be used simply to output a voice from an input text using a provided desktop TTS program.[9]


Languages include US and UK variants of English, Mexican Spanish, Canadian French, Chinese, Korean, and Japanese, with a variety of male and female voices.

The software is available for

See also[edit]


External links[edit]