Viewing profile — davidz
davidz
HN member- Joined
- Thu, Feb 22, 2007, 7:58 AM UTC
- HN karma
- 111
- Public activity
- 37 items
- HN profile
- View on Hacker News ↗
About davidz
No profile information was provided.
Recent public activity
- story
-
comment
Comment #46792435
we gotchu: https://docs.livekit.io/agents/models/tts/inference/inworld/
-
comment
Comment #46788562
no reasons to put open stack in quotes. code available under Apache-2 https://github.com/livekit/livekit
-
story
Show HN: Serverless platform for running voice AI agents
Over the past year, we've collaborated with hundreds of developers building voice AI agents using our Agents SDK. It quickly became apparent that hosting these persistent, session-…
-
comment
Comment #43981011
thanks for the feedback. let us see how we can organize this better for compat with diff LLMs.
-
comment
Comment #42938502
It's really cool to see how you guys are using the voice AI stack to overcome language barrier. (btw I work at LiveKit, so let me know if we could make Agents easier to use for you…
-
comment
Comment #41751872
currently we are using silero VAD to detect speech: https://github.com/livekit/agents/blob/main/livekit-plugins/... it works well for voice activity; though it doesn't always detec…
-
comment
Comment #41746393
I'm working on a PR now :)
-
comment
Comment #41746382
Currently it does: all audio is sent to the model. However, we are working on turn detection within the framework, so you won't have to send silence to the model when the user isn'…
-
comment
Comment #41716602
only if you buy enough tokens.
-
comment
Comment #32997255
Speculating here, but I would read this as "anycast" as a concept, where each user is connected to the closest location. versus anycast as in the IP protocol. The complexity far ou…
-
comment
Comment #31449552
Thanks Roshan!
-
comment
Comment #31449542
Arcas is fantastic! They are doing some really great work with WebRTC.
-
comment
Comment #28602092
> However, it's still a lowest common denominator solution with respect to what codec is being used. The broadcasting "peer" has to send using a codec that every other peer support…
- story
- story
-
comment
Comment #19936605
It's fine to dislike Medium and run your own blog, but I find the article intellectually dishonest in comparing Medium to Facebook. One harvests your data and lets advertisers targ…
- story
-
comment
Comment #12750191
"How quickly can we get this into people's hands? If you read the papers, you see maybe it's three years, maybe it's thirty years. And I am here to tell you that honestly, it's a b…
-
comment
Comment #12134976
The product isn't solar panels, it's energy. With a huge fleet of electric cars needing to be charged in major metros, where is the electricity coming from? What if you also have a…
-
comment
Comment #6382232
Voxel (Palo Alto, CA) - Local We run mobile apps in the cloud (virtualized) so you could use them without first downloading the binaries. Help us change how people create and distr…
-
comment
Comment #6357563
Thanks, we do as well. However, we'll remain very focused on ads initially to bring it to the masses.
- story
-
comment
Comment #3572629
Link: http://www.gemfury.com
- story