The discriminator works across audio generated by other text-to-speech products as well or does it depend on like a signal that you're embedding in. It catches some stuff what we noticed from like testing it from our models and from other other stuff on the market but it can get a little bitter I think this is just like the first version of it like this can get a lot bitter and detecting because these voices generated through transformers book orders.

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode