Tencent Zhiying announces major upgrade of voice model: more natural and fluent, with richer intonation and emotion

Tencent Smart FilmAnnounceSound ModelA major upgrade, with specific improvements including more natural fluency, richer emotional intonation, fewer voice defects and better adaptability.

The new version has a more natural and coherent voice, richer intonation and emotion, reduces the probability of speech defects, and can better adapt to different text content and contexts.

At the same time, Zhiying also launched two new free voices, a passionate female voice and a cute and friendly female voice, which are suitable for conversation and chatting scenarios.

Tencent Zhiying announces major upgrade of voice model: more natural and fluent, with richer intonation and emotion

In addition, the sound customization effect has also been upgraded, with the sampling rate upgraded from 16K to 24K, and users can customize the tone with the same upgraded effect.

Overall, the upgrade of Zhiying's sound model does not increase the price, making the sound more natural and expressive, allowing users to experience better sound effects when creating dubbing works.

statement:The content is collected from various media platforms such as public websites. If the included content infringes on your rights, please contact us by email and we will deal with it as soon as possible.
Information

Alibaba invested in Kimi AI developer Dark Side of the Moon: $800 million to purchase approximately 36% shares

2024-5-24 8:50:27

Information

Microsoft Edge will use AI to translate the YouTube videos you watch in real time

2024-5-24 8:54:26

Search