New Expressive Real-Time Text-to-Speech (TTS) Models Support High-Fidelity Voice Cloning

Zyphra, a company based in Palo Alto, California, building a mew multimodal artificial intelligence agent system, announced the release of Zonos-v0.1 beta, a pair of extremely expressive text-to-speech (TTS) models with high fidelity voice cloning. The company is releasing both the transformer and hybrid TTS models with an Apache 2.0 license, which effectively makes these available for redistribution.

BdSound and Vivoka, two European pioneers in voice technology, announced a strategic partnership to reshape the landscape of voice assistants. Through this collaboration, BdSound will leverage Vivoka's development framework allowing users to high-level construct tailored voice assistants. And BdSound's audio and speech processing technology will become an integral part of the acoustic front-end tools offered by Vivoka, promising to make voice assistants more accessible and customizable than ever before.

Yamaha Corporation announced that it has succeeded in reproducing the singing of the late Hibari Misora, a legendary Japanese vocalist, using its own VOCALOID:AI singing synthesis technology in technical cooperation with an NHK (Japan Broadcasting Corporation) television program broadcast in Japan on September 29, serving as both the public debut and first real-world implementation of VOCALOID:AI - an extension of the company's original singing voice synthesis technology.

Yamaha re-created the singing voice of deceased Japanese musician “hide” (Hideto Matsumoto) using its unique singing voice synthesizer technology Vocaloid to complete unrecorded and unreleased songs. Analyzing in detail the massive amount of digital vocal data that the Japanese singer recorded during his lifetime, Yamaha was able to re-create his voice using Vocaloid technology.