OpenAI built a voice cloning tool, but you can’t use it… yet
Recently, OpenAI has introduced its new AI model Voice Engine which was previously developed by OpenAI in late 2022. This model is an expansion of the company’s previous text-to-speech model.
The new OpenAI Voice Engine allows its users to synthetic voice of any voice. With this voice cloning tool, the users can upload any voice of up to 15 seconds, and this tool will generate a synthetic copy of that voice. This sounds truly amazing that with such a short sample this tool can generate more realistic and emotional audio.
Read more: A Big Question – Is AI Art Unethical?
“We take a small audio sample and text and generate realistic speech that matches the original speaker,” said Harris. “The audio that’s used is dropped after the request is complete.”
In their blog Post OpenAI has said that-” We recognize that generating speech that resembles people’s voices has serious risks, which are especially top of mind in an election year. 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 is testing this voice cloning tool with their trusted partners so that they can check the potential use of this tool. They have tested the voice engine for many purposes which they have also shared in their blog post. Some of the cases where the OpenAI voice engine is tested are:
The new Voice Engine is helping non-readers and children through natural-sounding, emotive voices to read the text aloud. This tool is helping them to study in a much better way. Many trusted companies are using the voice engine to create high-quality academic content for children.
Also, with this voice cloning tool, you can convert the podcast and news in different languages with original speaker voices to get a global reach for your content. Companies like HeyGen are already using their services.
OpenAI claims that the Voice Engine is helping the patients regain their voice. Doctors have successfully recovered the speech of a young patient who lost her voice due to a vascular brain tumor. Additionally, apart from these usages, OpenAI has listed many more uses of the voice cloning tool in their blog post.
However, for now the OpenAI is not releasing the tool for public use, as it’s still in the testing phase. The company wants people to become more familiar with the safety and right usage of voice cloning tool.
Read More: The AI craze has impacted the US government, Every US federal agency must hire a chief AI officer
“What’s going to keep pushing us forward in terms of the actual voice matching technology is really going to depend on what we learn from the pilot, the safety issues that are uncovered and the mitigations that we have in place,” he said. “We don’t want people to be confused between artificial voices and actual human voices.”
