After previewing its new Audiobox generative AI venture final month, which may replicate your voice utilizing simply seconds of pattern audio, Meta has now launched a publicly accessible demo of the method, which allows you to create customized audio samples based mostly by yourself voice and/or textual content prompts.
As defined by Meta:
“Audiobox is Meta’s new basis analysis mannequin for audio technology. It could possibly generate voices and sound results utilizing a mixture of voice inputs and pure language textual content prompts – making it simple to create customized audio for a variety of use instances.”
And it’s fairly good, although additionally fairly freaky.
First off, the Audiobox demo gives entry to a variety of parts, together with voice descriptions, sound impact technology, audio enhancing, and extra.
The principle pattern use case is customized audio technology based mostly on textual content prompts
As you may see on this instance, Meta has offered a couple of primary Audiobox check parts, together with a text-to-speech course of that allows you to generate customized audio based mostly on any textual content enter.
There are solely two system voices to make use of within the demo, “Alice” or “Emily”, nevertheless it provides you an concept of what the method can do, by way of translating customized textual content into various audio streams.
You can too add customized sounds to your pattern, once more based mostly on textual content prompts.
However the freaky half is the choice to generate your individual voice:
It undoubtedly seemed like me, and I undoubtedly didn’t prefer it. This, after all, may find yourself being a major concern, by way of potential misuse, and Meta does make you conform to a variety of phrases and situations of use earlier than attempting it.
But it surely’s fairly good, fairly correct. Uncomfortably so.
It’s the newest in Meta’s rising slate of generative AI instruments, that are set to see various use instances in its apps over the following 12 months. And whereas Meta’s nonetheless constructing in safety parameters, it’s a concern that it’s making such instruments extra extensively accessible, even with the varied phrases of service situations connected.
I’m unsure the world is prepared for it, in all honesty, and with varied elections developing, I can think about a variety of points arising from potential misuse.
However AI improvement is shifting quick, and Meta desires to maintain up.
If you wish to see how good it’s at replicating your voice, you may check it out for your self right here. Name your associate and play the snippet down the road, see if they’ll decide that it’s not truly you.
