On November 19, JPchain Co., Ltd. released the next generation speech synthesis AI platform “Aivis Project” developed by the company. Currently, the desktop application “AivisSpeech”, the web platform “AivisHub”, and the speech model creation tool “AIVM Generator” are available. “AivisSpeech” can be downloaded and used for free from the company’s website.
“AivisSpeech” is a high-performance AI speech synthesis software that runs in a Windows/Mac compatible local environment. The quality is so high that it is indistinguishable from a human voice, and it is said that English words, proper nouns, dates, etc. can be read naturally. Operation is intuitive, and you can make precise changes to the speaker’s style, speaking speed, pace, volume, silence before and after, and accent for each sentence. Although unofficial, it is also possible to link to “Yukkuri MovieMaker4” (YMM4). The software can be used freely without the need for credits, whether for individuals, corporations or commercial purposes.
“AivisHub” is a web platform that allows you to distribute and download speech synthesis modules. All models have the same license (ACML / ACML-NC / public domain (CC0)), so you can use them without worrying about differences in use cases, and you can publish speech synthesis models in AIVM / AIVMX format that can be used with “AivisSpeech” etc. In addition, features are being developed such as the ability to listen to voice samples and insert them directly into the “AivisSpeech” run from the model’s details page.
In addition, there is a web service called “AIVM Generator” that can generate AIVM/AIVMX files, an open file format for sharing AI speech synthesis models. In addition, we currently have “AivisBuilder,” which allows you to create a voice synthesis model even from mixed voice data that has not been recorded for voice model generation, and “Aivis API,” which allows you synthesize voice. high-speed modules on a high-performance GPU server using the API are also under development.
These services are intended to be used in a variety of settings, including video production, commentary and guidance for game development, podcasts, audiobooks, informational broadcasts, and demo audio production.
How does “AivisSpeech” address the “uncanny valley” effect often associated with synthetic speech, and what steps were taken to achieve a truly natural-sounding voice?
## Interview with the Developers of “Aivis Project”: A New Era for AI Speech Synthesis?
**Introduction:**
Welcome to World Today News. Today, we’re diving into the exciting world of AI speech synthesis with the creators of “Aivis Project”, a revolutionary new platform that promises to change the way we interact with technology. Joining us today are [Guest 1 Name and Title], and [Guest 2 Name and Title] from JPchain Co., Ltd.
**Section 1: The Power of “AivisSpeech”**
* **For our viewers who are unfamiliar with AI speech synthesis, can you give us a brief explanation of what “AivisSpeech” is and what makes it different from other similar software?**
* **”AivisSpeech” boasts near-human quality voice synthesis. What were the biggest technical challenges in achieving this level of naturalness, and how did your team overcome them?**
* **The article mentions that “AivisSpeech” can be used freely for both personal and commercial purposes without the need for credits. What motivated this open access approach, and what impact do you hope it will have on the creative community?**
**Section 2: A Collaborative Ecosystem: “AivisHub” and “AIVM Generator”**
* **”AivisHub” allows users to share and download pre-made voices, fostering a collaborative community around speech synthesis. What benefits do you see in this open-source approach, and how do you ensure quality control within the platform?**
* **”AIVM Generator” enables users to create their own unique voices. Can you elaborate on the process of creating a voice model, and what kind of expertise is required for users to effectively leverage this tool?**
**Section 3: Future Possibilities:**
* **The article mentions future developments, such as “AivisBuilder” and “Aivis API”. Can you give us a glimpse into the future of “Aivis Project” and how these ongoing developments will further expand the capabilities of the platform?**
* **What potential applications do you see for “Aivis Project” beyond the fields mentioned in the article, such as video games, podcasts, and audiobooks?**
* **Some concerns have been raised about the potential misuse of realistic AI voices, such as creating deepfakes or spreading misinformation. How does JPchain Co., Ltd. plan to address these ethical concerns as “Aivis Project” evolves?**
**Conclusion:**
Thank you, [Guest 1 Name] and [Guest 2 Name], for sharing your insights into this fascinating technological advancement.
“Aivis Project” certainly seems poised to revolutionize the way we interact with technology. We are eager to witness its impact on various industries and creative pursuits in the years to come.