AI News

Philipp Schmid calls the Pipecat demo a good example of Google Decision 1's audio capabilities

Philipp SchmidUpdated Nov 13 09:19

AI summary

Philipp Schmid reposted Jon Taylor's post and commented that this is a very good example of Google Decision 1's audio capabilities. The original post introduced the newly added PerceptionReader in Pipecat 1.16, which was tested with Google Decision 1 and can make fairly accurate judgments about the prosody, tone, and sarcasm in a user's speech.

Quoted post

Jon Taylor

@JonPTaylor

Pipecat 1.16 adds PerceptionReader, something I'm really excited about. How someone speaks can matter just as much as what they say, and voice agents have mostly been missing that. We’ve been testing it with Google Decision 1, released yesterday. Stream it audio and you get a pretty accurate read on the prosody, tone and sarcasm of what the user said. Try talking to it at this demo here: https://t.co/VlsJz3j054 We've exploring many different ways of measuring expressivity... more to share on that soon! ➡️ Pipecat Docs: https://t.co/AuIwJOcJvW ➡️ Google Decision 1: https://t.co/UjE85OEriS

View original

Pipecat 1.16 adds PerceptionReader, something I'm really excited about. How someone speaks can matter just as much as what they say, and voice agents have mostly been missing that. We’ve been testing it with Google Decision 1, released yesterday. Stream it audio and you get a pretty accurate read on the prosody, tone and sarcasm of what the user said. Try talking to it at this demo here: https://t.co/VlsJz3j054 We've exploring many different ways of measuring expressivity... more to share on that soon! ➡️ Pipecat Docs: https://t.co/AuIwJOcJvW ➡️ Google Decision 1: https://t.co/UjE85OEriS

View original post

Body

Great example for the Google Decision 1 audio capability.

Source

Philipp Schmid