OpenAI Testing AI-Generated Voice Mimicry in Limited Private Preview

OpenAI is testing a new AI-based voice technology in an effort to explore its capabilities while keeping it out of the hands of potential bad actors.

Voice Engine "uses text input and a single 15-second audio sample to generate natural-sounding speech that closely resembles the original speaker," OpenAI said in a blog post last week. It can create new audio from text using a single person's voice for reference, translate existing audio into another language while retaining the original speaker's tone and accent, or create new audio in a language that's different from the original speaker's.

Voice Engine has been around for a few years; its technology underlies OpenAI's text-to-speech API and ChatGPT's voice querying capability that was introduced last fall. At the end of 2023, however, OpenAI decided to start priming Voice Engine for eventual public consumption, beginning with just a "small group of trusted partners."

OpenAI did not indicate how long this limited private preview will last, or when it expects to make Voice Engine generally available. It is purposely taking a slow and measured approach "due to the potential for synthetic voice misuse," it said. OpenAI took a similar tack when launching its Sora text-to-video capability in February, making it available to only select testers.

Nevertheless, the Voice Engine testing group has already begun applying the model to a few real-world applications across several industries. For instance, it's being used to help patients with speech conditions to communicate with their own voice, using old video recordings of them as the reference audio. Content creators are also using it to translate their assets into different languages, giving them a broader audience. Other examples, with real audio snippets of Voice Engine in action, are on OpenAI's blog post.

For all its capabilities, however, this technology, like Sora, is ripe for abuse. OpenAI said it is working to develop guardrails for Voice Engine to limit how much it can contribute to the spread of misinformation. For instance, Voice Engine prevents individual users from making their own voices from scratch. In addition, audio created by Voice Engine comes with "watermarks" to track each snippet's provenance, as well as how it's being used.

OpenAI said it gave its testing group access to Voice Engine under several stipulations to discourage them from abusing the technology. For instance, they are not allowed to use Voice Engine to impersonate another party without their explicit consent. Testers also have to disclose to their audience when they're using Voice Engine to create audio.

To avoid widespread harm caused by AI-generated audio in general, OpenAI makes several suggestions for policymakers and developers:

  • Enforce a "no-go voice list" to prevent the impersonation of well-known figures.
  • Avoid voice-based authentication for critical systems.
  • Develop ways for individuals to protect the ownership of their voice.
  • Spread broad public awareness of AI misuse.
  • Fast-track the development of technology that can trace the provenance of audio and visual media.

"We recognize that generating speech that resembles people's voices has serious risks .... We are engaging with U.S. and international partners from across government, media, entertainment, education, civil society, and beyond to ensure we are incorporating their feedback as we build," OpenAI said.

About the Author

Gladys Rama (@GladysRama3) is the editorial director of Converge360.

Featured

  • glowing blue nodes connected by thin lines in an abstract network on a dark gray to black gradient background

    Report: Generative AI Taking Over SD-WAN Management

    In a few years, nearly three quarters of network operators will use generative AI for SD-WAN management, according to a new report from research firm Gartner.

  • abstract pattern with interconnected blue nodes and lines forming neural network shapes, overlaid with semi-transparent bars and circular data points

    Data, AI Lead Educause Top 10 List for 2025

    Educause recently released its annual Top 10 list of the most important technology issues facing colleges and universities in the coming year, with a familiar trio leading the bunch: data, analytics, and AI. But the report presents these critical technologies through a new lens: restoring trust in higher education.

  • abstract image representing AI tools for reading and writing

    McGraw Hill Introduces 2 Gen AI Learning Tools

    Global education company McGraw Hill has added two new generative AI tools to help personalize learning experiences for both K–12 and higher ed students, according to a news release.

  • abstract image of fragmented, floating geometric shapes with holographic lock icons and encrypted code, set against a dark, glitchy background with intersecting circuits and swirling light trails

    Education Sector a Top Target for Mobile Malware Attacks

    Mobile and IoT/OT cyber threats continue to grow in number and complexity, becoming more targeted and sophisticated, according to a new report from Zscaler.