OpenAI has developed a platform called Voice Engine that can use artificial intelligence to create a clone of a synthetic human voice based on just a 15-second sample.
A voice created by artificial intelligence can read text prompts in the same language as the speaker or in another language on command.
Jeff Harris, a member of the OpenAI Voice Engine product team, noted that the model was trained on a combination of licensed and publicly available data. The model is currently only available to about 10 developers.
AI text-to-speech generation is an area of generative AI that continues to evolve. While most focus on instrumental or natural sounds, there is less focus on voice generation. Some of the names in this space include companies like Podcastle and ElevenLabs, which offer artificial intelligence voice cloning technology and tools.
At the same time, the US government is trying to curb the unethical use of AI speech technology. Last month, the Federal Communications Commission banned robocalls that use AI voices after people received spam calls from an AI-cloned voice of President Joe Biden.
Source: The Verge
