Skip to main content
Bluvy Tube
Press Esc to exit fullscreen
Volume m
/
i
Theater mode t
f
/
Real speech-to-speech + accurate tool calling + low latency is a hard combo. PipeCat's phone-call LLM does it via a cascading pipeline GPT-level tool accuracy, low latency, cheap.Turns out you don't need native S2S to ship good voice agents. #voice #llm #ai #agents

Keyboard shortcuts

Space K
Play / pause
← →
Back / forward 5 s
J L
Back / forward 10 s
0–9
Jump to 0%–90% of the video
Home End
Start / end
, .
Previous / next frame (while paused)
< >
Slower / faster
↑ ↓
Volume
M
Mute / unmute
C
Captions
F
Fullscreen
I
Picture-in-picture
T
Theater mode
?
Show this help

Real speech-to-speech + accurate tool calling + low latency is a hard combo. PipeCat's phone-call LLM does it via a cascading pipeline GPT-level tool accuracy, low latency, cheap.Turns out you don't need native S2S to ship good voice agents. #voice #llm #ai #agents

Hemanth HM

Hemanth HM

@gnumanth.bsky.social

Subscribe
0 views Published on 28/08/2026 19:07
#ai #agents #voice #llm
Real speech-to-speech + accurate tool calling + low latency is a hard combo. PipeCat's phone-call LLM does it via a cascading pipeline GPT-level tool accuracy, low latency, cheap.Turns out you don't need native S2S to ship good voice agents. #voice #llm #ai #agents
2 comments
?
@record-lab.bsky.social · 28/08/2026 19:16
A cascade is a credible way to ship this. The useful proof would be p95 speech-to-action latency and completed tool tasks during interruptions. Those numbers would make "GPT-level" concrete and clarify the pipeline's trade-off.
View original post on Bluesky
Link copied to clipboard

Sign in

Time to take a break

You've been watching videos for 30 minutes straight: give yourself 5 minutes away from the screen. Stand up, stretch, grab a glass of water… Your videos will be right here when you're back.