Voice Cloning Tool from OpenAI: Voice Engine

When it comes to artificial intelligence, the first company that comes to mind is undoubtedly OpenAI. The technology giant is literally pioneering the new era we have entered with its models in many different areas, from chat bots to visual production. We last saw him with the “Sora” model, which creates jaw-droppingly realistic videos.

OpenAI has now announced a brand new model. “Voice EngineThis tool, called “, copies the human voice realistically.

Can clone real human voice in 15 seconds

This isn’t the company’s first foray into audio focus. It already had AI-powered voice tools. The feature that allows us to talk with ChatGPT is the best example of this. Voice Engine is also part of the company’s efforts to generate voice from text. According to OpenAI, this tool is actually Testing on a small group since 2022.

Let’s briefly explain what Voice Engine is. This tool is actually a voice cloning model. Only It can indistinguishably replicate a real person’s voice with a 15-second sample.. After this, the user can enter any text he wants and have the duplicate voice produced by artificial intelligence read whatever he wants. It is also possible to translate the cloned voice into different languages.

In its blog post, OpenAI also gave information about where the model can be used. Among these reading assistance, content translation, helping people with speech disorders There are targets such as.

OpenAI not launching Voice Engine yet due to security concerns

Voice Engine, not widely available. The company states that the main reason for this is the risks that such cloning technology will bring. He even adds that he initially planned to create a program that developers could participate in, but canceled it due to possible problems. The group currently being tested has already signed agreements prohibiting the use of voice without their consent.

Security is a really serious problem. We know how advanced deepfake technologies are today. We see fake images and sounds everywhere. Inappropriate content imitating famous names, fraudulent images and selser are the best examples of these. That’s why OpenAI’s Voice Engine model is so risky. The company is also aware of this. That’s why they don’t have any plans to release it on a large scale yet. So we don’t know when it will come.

OpenAI shared the voice recordings created with Voice Engine on its site. Link here You can access the examples by clicking. In the recordings shared in pairs or triples, the ones at the top belong to real people, and the ones at the bottom shared as “Generated audio” belong to artificial intelligence.