Live data from Hacker News

Viewing profile — KianHooshmand

KianHooshmand

HN member
Joined
Mon, May 24, 2021, 12:48 AM UTC
HN karma
226
Public activity
33 items

About KianHooshmand

No profile information was provided.

Recent public activity

  1. comment
    Comment #39219436

    Vocode || Engineering (multiple roles) || SF/Remote || Full-time/Contract || https://vocode.dev We (Vocode) empower developers to connect the world with magical conversational AI e…

  2. comment
    Comment #38851665

    Vocode || Engineering (multiple roles) || SF/Remote || Full-time/Contract || https://vocode.dev We (Vocode) empower developers to connect the world with magical conversational AI e…

  3. job
  4. story
  5. comment
    Comment #35407169

    In the main post! It's +1-650-729-9536 :)

  6. story
  7. comment
  8. comment
    Comment #35374631

    Yes! Give it a try on the phone call and let us know what you think – would love feedback!

  9. comment
    Comment #35374625

    thank you! All credit to Rime for the Gen Z voice :)

  10. comment
    Comment #35374612

    Yep. We are working on adding more integrations (and want to have a full self hosted stack)... we're open to contributors and help from the community if there's something you'd lik…

  11. comment
    Comment #35368384

    absolutely! you can just plug in your own LLM... so it can be trained on anything you like and the library will make it voice-based!

  12. comment
    Comment #35368045

    Thank you for the feedback! Actually it can be configured to use any transcriber you like... Twilio just pipes the audio to us and we can use any of our integrations (Deepgram, Whi…

  13. comment
    Comment #35367840

    totally agree! this is a really cool use case :)

  14. comment
    Comment #35366498

    We chunk it up per sentence so it has some context!

  15. comment
    Comment #35366213

    Lily is epic. Highly recommend checking out Rime when it's available!!

  16. comment
    Comment #35365846

    Totally! We actually use LangChain for the OpenAI wrapper agents we give out of the box (you can plug in your own custom one as well)

  17. comment
    Comment #35363587

    thank you!

  18. comment
    Comment #35363579

    We definitely want to do this! We've been talking about it (it's much better like you said for realtime); it's been hard to juggle everything we've wanted to add.. which is why we …

  19. comment
    Comment #35363249

    Yep we're definitely getting a large volume right now – working on it!

  20. comment
    Comment #35363232

    Ah! Right now our default is set to use OpenAI... but you can actually use local LLMs by creating a custom agent. We're going to add a full stack of local STT/TTS/LLM... just haven…

  21. comment
    Comment #35363193

    thank you! love your feedback and please feel free to drop any questions in discord/on github

  22. comment
    Comment #35363181

    thank you! it's not live right now... but stay tuned for april 1 :)

  23. comment
    Comment #35361955

    Thank you!! Really glad you enjoyed it We actually have no clue... but it seems to be holding up well. We can scale up the CPU as necessary but not sure about Twilio. I guess we wi…

  24. comment
    Comment #35361938

    We totally agree – thank you for the feedback! :)

  25. comment
    Comment #35361398

    thank you for the kind words! absolutely agree – we're gonna beef up our tutorials and documentation... just have had so much to do but it's definitely one of our focuses now. stay…