Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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...

17,381 Aufrufe • vor 5 Tagen •via X (Twitter)

9 Kommentare

Profilbild von Jon Taylor
Jon Taylorvor 5 Tagen

Code is here:

Profilbild von Philipp Schmid
Philipp Schmidvor 4 Tagen

Well done! And great example for the Google Decision 1 audio capability.

Profilbild von Pablo Giménez
Pablo Giménezvor 4 Tagen

Sarcasm is the one I'd test first. In Spanish a lot of it lives only in the intonation, the words themselves are perfectly polite. Does it hold up outside English?

Profilbild von Neil Stoker ✨
Neil Stoker ✨vor 4 Tagen

Nice demo! ✨ Would be great to see metrics for "focused" and/or "confused" - those could be pretty useful for conversational strategies and allowed user activities

Profilbild von AJ
AJvor 4 Tagen

How are you acting on this sentiment information? I built a classifier for function_tool selection because LLMs accuracy at selecting tools is quite poor

Profilbild von yung algo
yung algovor 4 Tagen

very nice

Profilbild von Thor 雷神 ⚡️
Thor 雷神 ⚡️vor 4 Tagen

Oh, this is awesome. Thanks so much for sharing. 🔥

Profilbild von Shawn Wen
Shawn Wenvor 4 Tagen

agreed. on phone calls the 'how' we need most is timing, so curious if these signals will feed smart turn too

Profilbild von Pete Haas
Pete Haasvor 4 Tagen

Great example of using the Decisions API. I could imagine extending this to non-verbal cues like sighs. I.E. A sigh before "sure" changes what the agent should do next. Have you tried reading wordless turns?

Ähnliche Videos