OpenAI, the pioneer of artificial technology, has launched Voice Engine, an extension of the company's current text-to-speech API, which offers users the capability to upload any 15-second voice sample, generating a synthetic replica of that voice.
The company on Friday announced, "Today we are sharing preliminary insights and results from a small-scale preview of a model called Voice Engine, which uses text input and a single 15-second audio sample to generate natural-sounding speech that closely resembles the original speaker. It is notable that a small model with a single 15-second sample can create emotive and realistic voices."
Voice Engine was initially developed in late 2022 and has since been utilized to empower the preset voices accessible in the text-to-speech API, along with ChatGPT Voice and Read Aloud functionalities.
The company sought to allay any concerns about the tool's abuse by saying, "we are taking a cautious and informed approach to a broader release due to the potential for synthetic voice misuse. We hope to start a dialogue on the responsible deployment of synthetic voices, and how society can adapt to these new capabilities."
To gain deeper insights into the potential applications of the technology, a private testing phase was initiated by the team late last year with a select group of trusted partners.
These initial pilot deployments are playing a crucial role in shaping the team's strategy, security measures, and conceptualisation of how Voice Engine could be used across different sectors.
"For example generating English with an audio sample from a French speaker would produce speech with a French accent," OpenAI, led by Sam Altman, said.
"Based on these conversations and the results of these small scale tests, we will make a more informed decision about whether and how to deploy this technology at scale," it added.
The company said it acknowledges risks associated with generating speech that mimics individuals' voices, particularly during an election year.
It also claimed that the partners currently testing Voice Engine have agreed to adhere to the usage policies set forth by the company.
These policies strictly prohibit the impersonation of individuals or organisations without proper consent or legal authority. Additionally, developers are prohibited from creating methods for individual users to generate their own voices.
OpenIAI said, "Voice Engine is a continuation of our commitment to understand the technical frontier and openly share what is becoming possible with AI. In line with our approach to AI safety and our voluntary commitments, we are choosing to preview but not widely release this technology at this time."
