🤖 OpenAI built a voice cloning tool, but you can’t use it… yet
OpenAI has previewed Voice Engine, a model for creating custom voices, which uses text input and a single 15-second audio sample to generate natural-sounding speech that closely resembles the original speaker. Notably, a small model with a single 15-second sample can create emotional and realistic voices.
🎙 Thus, it will be possible to pronounce any text with your synthesized voice.
No public launch date has been announced yet, but there are already cases of Voice Engine application:
⚪️ Age of Learning, an education technology company dedicated to children's academic success, has been using this to generate pre-scripted voice-over content.
⚪️ HeyGen, a platform for creating digital avatars, applies Voice Engine to translate videos into different languages while preserving the speaker's intonation.
🛡 The news sounds like a new opportunity for fraudsters. Therefore, much of OpenAI's announcement was devoted to the responsible usage of synthetic voices and society's adaptation to this technology.
They suggest:
✅ phasing out voice-based authentication as a security measure for accessing bank accounts;
✅ exploring policies to protect the use of individuals' voices in AI;
✅ educating the public in understanding the capabilities and limitations of AI technologies,
OpenAI continues to test and discuss Voice Engine with partners to make an informed decision about the scope of its future deployment.
Source: https://openai.com/blog/navigating-the-challenges-and-opportunities-of-synthetic-voices
🔥 — great, there's no stopping progress
🎃 — dangerous, they shouldn't be doing this
