Загрузка видео...

Не удалось загрузить видео

На главную

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 просмотров • 5 дней назад •via X (Twitter)

Комментарии: 9

Фото профиля Jon Taylor
Jon Taylor5 дней назад

Code is here:

Фото профиля Philipp Schmid
Philipp Schmid4 дней назад

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

Фото профиля Pablo Giménez
Pablo Giménez4 дней назад

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?

Фото профиля Neil Stoker ✨
Neil Stoker ✨4 дней назад

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

Фото профиля AJ
AJ4 дней назад

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

Фото профиля yung algo
yung algo4 дней назад

very nice

Фото профиля Thor 雷神 ⚡️
Thor 雷神 ⚡️4 дней назад

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

Фото профиля Shawn Wen
Shawn Wen4 дней назад

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

Фото профиля Pete Haas
Pete Haas4 дней назад

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?

Похожие видео