San Francisco, CA – OpenAI is set to expand its ChatGPT voice library with the addition of eight new voices, according to a recent report from tech publication testingcatalog. The new voices, discovered through reverse engineering of the ChatGPT app, are designed to offer a more naturaland expressive reading experience.
Each of the new voices has a unique code name and is expected to be rolled out gradually. What makes these voices particularly interesting istheir ability to express a wider range of sounds, including animal noises and other non-verbal sounds, with greater realism. This suggests a potential shift in the capabilities of text-to-speech (TTS) technology, moving beyond human voices to encompass abroader spectrum of sounds.
These new voices are a significant step forward in TTS technology, said Dr. Emily Carter, a leading AI researcher at Stanford University. The ability to generate animal sounds and other non-verbal sounds with such realismopens up exciting possibilities for applications in entertainment, education, and accessibility.
While the new voices are expected to enhance the user experience, it’s important to note that they remain TTS voices and are not related to the advanced voice models currently in alpha testing. This means they are not capable of real-time interaction oremotional nuance like the more advanced models.
The addition of these new voices is a testament to OpenAI’s ongoing commitment to pushing the boundaries of AI technology. As the company continues to refine its models, we can expect even more innovative and immersive voice experiences in the future.
References:
- Testingcatalog. (2024, September 2). OpenAI ChatGPT to Add 8 New Voices, Including Animal Sounds. [Blog post]. Retrieved from [insert URL]
- IT之家. (2024, September 3). OpenAI ChatGPT 被曝将新增 8 种新语音：更自然表达狗叫等动物声音. [News article]. Retrieved from [insert URL]
Views: 0