"Having a distinctive voice is like getting something back that was stolen," John said. The voice came eight years after he was diagnosed with ALS and more than six years since his voice had become unintelligible to everyone except his wife and youngest son. Pandya has gone on mission trips to South America, and she started a service organization at her school. They also become identities for people with speech disorders who rely on technology to communicate. But the aspiring biomedical engineer said she was inspired to help someone speak and also fascinated by the technology and the ability to combine voices. The effort to build an international "Human Voicebank" has attracted more than 17,000 volunteers from 110 countries. Since Patel announced the voicebank two years ago, the response has been overwhelming, she said, with donors ages 6 to 91 logging on all over the world. Then those sounds are blended with a larger sample - usually six to 10 hours of recordings - from a voice donor, matched by age, sex and region. Patel said she is continuing to simplify the process to build voices more cost-effectively and efficiently. She wanted to gain access to enough voices to reflect the diversity of potential customers, which could include a middle-aged man from Alabama or a little girl from Ireland. Some have throat cancer or degenerative diseases such as ALS and could eventually receive voice help themselves. When she decided to bring the technology out of the lab, she developed her own method for blending voices and turned to crowdsourcing for help. "Even people who are speechless have sounds that are unique to them." The main character, a teenager with cerebral palsy, relies on technology and a personal aide to act as his "voice" at school. They merge the voices by modifying the donor voice to reflect the qualities of the user's voice.