ME News reports that on July 22 (UTC+8), according to monitoring by Beating, ByteDance Seed has released Seed Audio 1.0, an audio creation model capable of generating dialogue, sound effects, and ambient noise from a single prompt, with precise timeline control over audio entrances. The model supports both text and reference audio inputs, with timing precision of 100ms. It can generate approximately two minutes of audio in a single run, with the ability to extend duration while maintaining consistent character voice quality. Seed Audio 1.0 supports over 20 languages, enabling cross-language voice transfer, as well as tone and emotion switching. Official evaluations show that audio usability exceeds 90% in most scenarios, with naturalness MOS scores surpassing 4 for most languages. The model is now available on the Volcano Ark Experience Center and offers API access. (Source: BlockBeats)
ByteDance Launches Seed Audio 1.0 for Multilingual Audio Generation
KuCoinFlashShare
ByteDance Seed launched Seed Audio 1.0 on July 22, a multilingual audio model that generates dialogue, ambient sounds, and effects from a single prompt. It supports over 20 languages with voice consistency and emotion control, and can produce two minutes of audio with 100ms precision. Over 90% of outputs are usable, achieving top scores in naturalness. As altcoins to watch rally, the tool is now available via API on the Volcano Ark Experience Center.
Source:Show original
Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information.
Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.