The Evolution and Current State of AI Voice Technology

NTT Texcroix Corporation has announced the launch of “SynoraVoice“, a software that allows real-time transformation of a speaker’s voice into a preferred voice and speaking style. The service is set to be available starting September 16, 2025. In recent years, AI technology has advanced in precision for speech recognition and synthesis, being utilized in various services. Traditional voice conversion methods faced limitations due to time-consuming processes and mechanical sounds, but NTT Texcroix has addressed these challenges, enabling natural and smooth conversations.

Features of Real-Time Conversion

“SynoraVoice” utilizes real-time voice conversion technology developed by NTT Communication Science Laboratories. This technology allows for instantaneous modification of the speaker’s tone and speaking style, facilitating seamless communication. It comes standard with eight voice models, enabling the selection of the most suitable voice based on the context. Additionally, it offers the flexibility to add new voice models and integrate seamlessly with other systems, such as web conferencing platforms.

Diverse Application Scenarios

NTT Texcroix presents various practical applications for “SynoraVoice,” including character voices in the metaverse and YouTube streaming, special effects for events, public announcements in transportation and public facilities, and voice conversion for call center operators. Notably, the flexible customization of voices is expected to enhance immersion, comprehension, and operational efficiency across various scenarios.

Future Prospects

NTT Texcroix is committed to actively expanding voice models and improving functionality to meet diverse needs. “SynoraVoice” is available solely through corporate licensing, with pricing structured based on usage types and the number of voice models used. For detailed pricing information, direct inquiries are required.

Thoughts and Expectations

“SynoraVoice” is an innovative software that fully capitalizes on the potential of AI voice technology. The ability to achieve natural conversation in real-time has the potential to significantly alter communication forms. Its anticipated contributions to the advancement of voice communication are exciting, and the expansion of usage scenarios across society is something to look forward to.

Source: PR TIMES