Today we’re introducing our latest Text-To-Speech model, Play 3.0 mini. It’s faster, more accurate, handles multiple languages, supports streaming from LLMs, and it’s more cost-efficient than ever before.
Try it out here:
I had this idea of The Unhuman Podcast, where I interview brand new LLMs like stars, as my quirky way of evaluating them.
I used
@fal
for speech-to-text & LLM interactions, and
@play_ht
's new Play 3 mini for text-to-speech to quickly make this short demo!
Interested in the future of voice agents? Exhausted from b2b meetings during tech week? Take a break and swing by our Palo Alto offices on 10/10 for food and insights — starting at 6pm!
cc:
@Techweek_