OpenAI unveils ‘Voice Engine’ text-to-voice AI model

OpenAI has introduced Voice Engine, a groundbreaking platform for text-to-voice generation.

This innovative system utilizes a mere 15-second clip of an individual’s voice to create a synthetic voice, marking another significant milestone following the successful debut of the ‘Sora’ text-to-video AI model earlier this year.

Features and Applications

Voice Engine empowers users with the ability to generate synthetic voices capable of reading text prompts in various languages, including the speaker’s native tongue.

OpenAI emphasizes its commitment to responsible deployment, acknowledging the potential for misuse while exploring the platform’s constructive applications.

Early Testing and Development

In late 2022, OpenAI initiated the development of Voice Engine, subsequently employing it to enhance preset voices within the text-to-speech API, ChatGPT Voice, and Read Aloud.

Through small-scale deployments and partnerships, the company gained insights into potential use cases across diverse industries. Notable early applications include:

Reading Assistance: Age of Learning utilizes Voice Engine to produce natural-sounding, emotive voices for pre-scripted voice-over content, aiding non-readers and children in learning. The technology also facilitates real-time, personalized interactions with students.

Content Translation: HeyGen leverages Voice Engine for video translation, enabling creators and businesses to reach global audiences fluently and authentically in multiple languages, while preserving the original speaker’s accent.

Community Health Services: Dimagi employs Voice Engine to enhance essential service delivery in remote areas by providing interactive feedback to community health workers in their native languages, including Swahili and Sheng.

Augmentative Communication: Livox utilizes Voice Engine to power AAC devices, offering individuals with disabilities unique and natural voices across multiple languages, enhancing communication and self-expression.

Voice Recovery: The Norman Prince Neurosciences Institute at Lifespan explores the use of Voice Engine in clinical contexts to restore speech for individuals with speech impairments due to medical conditions such as brain tumors.

Ensuring Safety and Responsibility

Recognizing the potential risks associated with synthetic voice technology, OpenAI prioritizes safety measures and responsible deployment.

Partners testing Voice Engine must adhere to strict usage policies, including obtaining explicit consent from original speakers and transparently disclosing AI-generated content to users.

OpenAI also implements safeguards such as watermarking to trace the origin of generated audio and actively monitors its usage to prevent misuse.

Future Prospects and Societal Considerations

OpenAI envisions Voice Engine as a testament to their commitment to exploring AI’s technical frontiers while prioritizing safety and ethical considerations.

Although the technology is previewed, not widely released, OpenAI encourages societal readiness to address the challenges posed by increasingly sophisticated generative models.

Suggestions for bolstering societal resilience include phasing out voice-based authentication, safeguarding individuals’ voices in AI, public education on AI capabilities and limitations, and advancing techniques for verifying audiovisual content authenticity.


Despite its groundbreaking capabilities, Voice Engine remains in a preview stage and is not yet available to the public.

OpenAI cites concerns regarding potential misuse of synthetic voices as the reason for this cautious approach, underscoring the importance of responsible AI deployment.