OpenAI’s Voice Cloning AI Model Requires Just a 15-Second Sample to Operate
April 8, 20243 min read 分钟阅读
Share
OpenAI is rolling out limited access to its text-to-voice generation platform called Voice Engine, as reported by The Verge. This innovative platform can synthesize a voice based on a 15-second audio clip, enabling the creation of realistic-sounding artificial voices. These AI-generated voices are capable of reading text prompts in multiple languages and have potential applications across various industries, according to OpenAI’s blog post.
Among the companies granted access to Voice Engine are Age of Learning, HeyGen, Dimagi, Livox, and Lifespan. OpenAI has showcased samples demonstrating how Age of Learning is utilizing the technology to produce pre-scripted voice-over content and deliver personalized responses to students generated by GPT-4.
Voice Engine development commenced in late 2022 and has since powered preset voices for text-to-speech APIs and ChatGPT’s Read Aloud feature. Jeff Harris from OpenAI’s Voice Engine product team revealed to TechCrunch that the model was trained on a combination of licensed and publicly available data. The platform will be limited to approximately 10 developers, according to OpenAI’s disclosure to the publication.
While AI text-to-audio generation continues to advance, voice generation has received less attention due to various concerns, as highlighted by OpenAI. However, companies like Podcastle and ElevenLabs are exploring AI voice cloning technologies, as previously explored on The Vergecast.
Simultaneously, the US government is taking measures to regulate unethical applications of AI voice technology. The Federal Communications Commission recently prohibited robocalls utilizing AI voices after instances of spam calls impersonating President Joe Biden’s voice.
OpenAI’s partners have committed to adhering to usage policies that prohibit impersonation without consent, requiring explicit and informed consent from original speakers, and disclosing AI-generated voices to listeners. To ensure accountability, OpenAI has implemented watermarking on audio clips and actively monitors their usage.
OpenAI suggests several measures to mitigate risks associated with such tools, including phasing out voice-based authentication for bank accounts, implementing policies safeguarding the use of individuals’ voices in AI, enhancing education on AI deepfakes, and developing AI content tracking systems.
In a recent cybersecurity incident, former Amazon security engineer Shakeeb Ahmed received a three-year prison sentence for hacking two cryptocurrency exchanges and stealing over $12 million. This case underscores the critical importance of robust cybersecurity measures for Enterprises operating in the digital landscape. Ahmed’s hacking techniques, including smart contract reverse engineering and blockchain audit skills, …
A server IP address serves as a unique identifier on the internet or local network, composed of a series of numbers to locate and recognize servers. Selecting the appropriate server IP type is crucial for guaranteeing server security, stability, and performance. This article delves into four prominent server IP types: native IP, broadcasted IP, dedicated IP, and shared IP. …
COMMENTARY While distributed denial-of-service (DDoS) attacks and zero-day threats are nothing new in cybersecurity, they’re still happening regularly for a simple reason: They work. In early November 2023, OpenAI blamed a DDoS attack for intermittent ChatGPT issues, and one of the largest known denial-of-service attacks hit major internet companies in October. The same group of …
OpenAI’s Voice Cloning AI Model Requires Just a 15-Second Sample to Operate
OpenAI is rolling out limited access to its text-to-voice generation platform called Voice Engine, as reported by The Verge. This innovative platform can synthesize a voice based on a 15-second audio clip, enabling the creation of realistic-sounding artificial voices. These AI-generated voices are capable of reading text prompts in multiple languages and have potential applications across various industries, according to OpenAI’s blog post.
Among the companies granted access to Voice Engine are Age of Learning, HeyGen, Dimagi, Livox, and Lifespan. OpenAI has showcased samples demonstrating how Age of Learning is utilizing the technology to produce pre-scripted voice-over content and deliver personalized responses to students generated by GPT-4.
Voice Engine development commenced in late 2022 and has since powered preset voices for text-to-speech APIs and ChatGPT’s Read Aloud feature. Jeff Harris from OpenAI’s Voice Engine product team revealed to TechCrunch that the model was trained on a combination of licensed and publicly available data. The platform will be limited to approximately 10 developers, according to OpenAI’s disclosure to the publication.
While AI text-to-audio generation continues to advance, voice generation has received less attention due to various concerns, as highlighted by OpenAI. However, companies like Podcastle and ElevenLabs are exploring AI voice cloning technologies, as previously explored on The Vergecast.
Simultaneously, the US government is taking measures to regulate unethical applications of AI voice technology. The Federal Communications Commission recently prohibited robocalls utilizing AI voices after instances of spam calls impersonating President Joe Biden’s voice.
OpenAI’s partners have committed to adhering to usage policies that prohibit impersonation without consent, requiring explicit and informed consent from original speakers, and disclosing AI-generated voices to listeners. To ensure accountability, OpenAI has implemented watermarking on audio clips and actively monitors their usage.
OpenAI suggests several measures to mitigate risks associated with such tools, including phasing out voice-based authentication for bank accounts, implementing policies safeguarding the use of individuals’ voices in AI, enhancing education on AI deepfakes, and developing AI content tracking systems.
Related Posts
Strengthening Cybersecurity Measures: Lessons from the Ex-Amazon Engineer’s Crypto Exchange Hacking Case
In a recent cybersecurity incident, former Amazon security engineer Shakeeb Ahmed received a three-year prison sentence for hacking two cryptocurrency exchanges and stealing over $12 million. This case underscores the critical importance of robust cybersecurity measures for Enterprises operating in the digital landscape. Ahmed’s hacking techniques, including smart contract reverse engineering and blockchain audit skills, …
Unveiling Server IP Types: A Comprehensive Guide and Best Practices
A server IP address serves as a unique identifier on the internet or local network, composed of a series of numbers to locate and recognize servers. Selecting the appropriate server IP type is crucial for guaranteeing server security, stability, and performance. This article delves into four prominent server IP types: native IP, broadcasted IP, dedicated IP, and shared IP. …
In Cybersecurity and Fashion, What’s Old Is New Again
COMMENTARY While distributed denial-of-service (DDoS) attacks and zero-day threats are nothing new in cybersecurity, they’re still happening regularly for a simple reason: They work. In early November 2023, OpenAI blamed a DDoS attack for intermittent ChatGPT issues, and one of the largest known denial-of-service attacks hit major internet companies in October. The same group of …