正在加载视频...

视频加载失败

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 次观看 • 5 天前 •via X (Twitter)

9 条评论

Jon Taylor 的头像
Jon Taylor5 天前

Code is here:

Philipp Schmid 的头像
Philipp Schmid4 天前

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

Pablo Giménez 的头像
Pablo Giménez4 天前

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 ✨ 的头像
Neil Stoker ✨4 天前

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 的头像
AJ4 天前

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 的头像
yung algo4 天前

very nice

Thor 雷神 ⚡️ 的头像
Thor 雷神 ⚡️4 天前

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

Shawn Wen 的头像
Shawn Wen4 天前

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

Pete Haas 的头像
Pete Haas4 天前

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?

相关视频