OpenAI has developed Voice Engine, a model that generates natural-sounding speech using text input and a 15-second audio sample. Early applications include reading assistance, translating content, reaching global communities, supporting non-verbal people, and helping patients recover their voice. OpenAI is committed to building Voice Engine safely and engaging with partners to incorporate their feedback. They also highlight the need for voice authentication experiences and policies to protect individuals' voices in AI technology. The technology is being previewed but not widely released at this time.
Sort: