Generative AI

OpenAI holds back public release of voice-cloning capability for its AI model

OpenAI has recently announced the development of a new text-to-speech AI model named "Voice Engine." The technology can generate synthetic voices based on just 15 seconds of recorded speech. The exact capabilities of the technology may still be under investigation. OpenAI has provided audio samples on its website but has not yet released the technology widely.
TL;DR (Meta-Llama-3.1-8B + RAG)