"OpenAI's New Voice Cloning Tool: Mimicking Human Voices with Just a 15-Second Sample"
TL;DR Summary
OpenAI has developed Voice Engine, a text-to-voice generation platform that can create a synthetic voice based on a 15-second clip of someone's voice. The AI-generated voice can read out text prompts in multiple languages and has been deployed by companies like Age of Learning and Dimagi. OpenAI is limiting access to about 10 developers and has implemented usage policies to prevent unethical uses, including impersonation without consent. The company also added watermarking to trace the origin of audio clips and suggested steps to limit risks associated with AI voice technology.
Topics:business#ai-voice-cloning#artificial-intelligence#ethical-use-of-ai#openai#text-to-voice-generation#voice-engine
- OpenAI's voice cloning AI model only needs a 15-second sample to work The Verge
- OpenAI Unveils Audio Tool That Recreates Human Voices The New York Times
- OpenAI previews Voice Engine generator, acknowledging risks NBC News
- OpenAI Previews New Audio Tool That Can Read Text, Mimic Voices Bloomberg
- OpenAI knows you're worried about AI-generated voices Business Insider
Reading Insights
Total Reads
0
Unique Readers
1
Time Saved
2 min
vs 3 min read
Condensed
81%
465 → 90 words
Want the full story? Read the original article
Read on The Verge