ajaynraj

ajaynraj on Hacker News

Re:Show HN: Zenfetch – Turn your saved browsing content into an AI sec... on Wednesday January 24, 2024 @12:59PM (#39120477)

This seems interesting! How are you dealing with hallucination? e.g. recalling a fact from an article that I have not necessarily read

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @10:23PM (#35367035)

thanks!!

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @10:22PM (#35367024)

thanks da :)

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @07:07PM (#35365183)

thanks!! obviously there's a lot of stuff we need to do to make this run at scale that Alexa has down pat.

A Home Assistant integration is a great idea! would love to talk with you on our Discord[0] about this / over email ( ajay at vocode.dev ), it's something we definitely want to build.

[0] https://discord.com/invite/NaU4mMgcnC

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @06:47PM (#35364960)

here's one from Twitter! https://twitter.com/altryne/status/1640880190401257473?s=20

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @04:35PM (#35363150)

thank you!! we also have another number which is prompted to act as a spokesperson for the product: (650) 835-7163

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @04:29PM (#35363043)

Ah, got it — that demo is a bit old and definitely has some bugs, my bad!

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @04:27PM (#35363001)

sorry you had that experience! Would love to help you get the bot running locally so we can figure out what's going on — here's our Discord: https://discord.gg/NaU4mMgcnC

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @04:23PM (#35362932)

would love to help you get it running as well! https://discord.gg/NaU4mMgcnC

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @04:04PM (#35362648)

The short answer is that everything is streaming — as tokens come back from ChatGPT we send them as soon as possible to the synthesizer. The long answer is found in our code[0] :).

[0] https://github.com/vocodedev/vocode-python/blob/main/vocode/...

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @03:21PM (#35361961)

thanks! we have a more "informational" phone number at +19105862633 that speaks a little slower (but sounds more robotic).

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @02:54PM (#35361578)

thanks!! Sampling rate actually shouldn't affect talking speed - you can adjust the voice speed with this parameter[0] :)

[0] https://github.com/vocodedev/vocode-python/blob/main/vocode/...

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @02:45PM (#35361463)

also! the code for the demo is available (and running!) at https://replit.com/@vocode/Gen-Z-Phone

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @02:41PM (#35361412)

the code for the demo is available (and running!) at https://replit.com/@vocode/Gen-Z-Phone

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @02:39PM (#35361378)

thank you!! websockets have been around forever but they're still so fast.

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @02:37PM (#35361348)

thank you!! The difference between a conversation with a command-based assistant and a conversational assistant backed by a LLM is subtly significant — you don't expect to have real conversations with the former and you actually engage with the latter.

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @01:06PM (#35360094)

Thanks! It's a collab with rime.ai TTS. Unlike a lot of other TTS providers, they train on conversation, not podcasts/audiobooks so you get those disfluencies in speech that make it seem natural!

Re:Launch HN: Vocode (YC W23) – Library for realtime voice conversatio... on Wednesday March 29, 2023 @12:54PM (#35359939)

Home Assistant is such a cool project :) great idea!

Show HN: PrankGPT – call your friends with GPT-3

Posted by ajaynraj on Friday January 13, 2023 @04:29PM
from the show-hn dept.

https://www.prankgpt.com/

PrankGPT calls a phone number and makes GPT-3 have a back-and-forth conversation with the call recipient. Use it to prank your friends!Demo: https://www.loom.com/share/0d0d68f1a62f409eb5ae24521293d2dcStack:- GCP for both Text-to-Speech and Speech-to-Text- Twilio for the telephony- GPT-3 davinci-003 model (no fine-tuning) from OpenAI (where most of the latency of the response comes from)Would...

( Read More... | no comments | 2 points | on HN )