Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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 görüntüleme • 5 gün önce •via X (Twitter)

9 Yorum

Jon Taylor profil fotoğrafı
Jon Taylor5 gün önce

Code is here:

Philipp Schmid profil fotoğrafı
Philipp Schmid4 gün önce

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

Pablo Giménez profil fotoğrafı
Pablo Giménez4 gün önce

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?

Neil Stoker ✨ profil fotoğrafı
Neil Stoker ✨4 gün önce

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

AJ profil fotoğrafı
AJ4 gün önce

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

yung algo profil fotoğrafı
yung algo4 gün önce

very nice

Thor 雷神 ⚡️ profil fotoğrafı
Thor 雷神 ⚡️4 gün önce

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

Shawn Wen profil fotoğrafı
Shawn Wen4 gün önce

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

Pete Haas profil fotoğrafı
Pete Haas4 gün önce

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?

Benzer Videolar