<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Hacker News: ssmaameri</title><link>https://news.ycombinator.com/user?id=ssmaameri</link><description>Hacker News RSS</description><docs>https://hnrss.org/</docs><generator>hnrss v2.1.1</generator><lastBuildDate>Thu, 10 Sep 2026 06:10:31 +0000</lastBuildDate><atom:link href="https://hnrss.org/user?id=ssmaameri" rel="self" type="application/rss+xml"></atom:link><item><title><![CDATA[Show HN: AI Landscape Design Generator]]></title><description><![CDATA[
<p>Working on an AI Landscape Design generator to help people come up with ideas for their gardens and landscapes<p>Just a basic set of features right now, but planning to keep adding more as time goes on</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=42202247">https://news.ycombinator.com/item?id=42202247</a></p>
<p>Points: 3</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 21 Nov 2024 08:28:24 +0000</pubDate><link>https://landscapedesignsai.com</link><dc:creator>ssmaameri</dc:creator><comments>https://news.ycombinator.com/item?id=42202247</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42202247</guid></item><item><title><![CDATA[Show HN: Voice Surveys Powered by AI Voice Agents]]></title><description><![CDATA[
<p>Built an app that let's create shareable surveys that user's can take over voice.<p>Could let you collect more personal, nuanced information v.s traditional text surveys.<p>They get a public link to your survey, where they interact with the voice powered AI agents, that also collects the survey results</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=42105171">https://news.ycombinator.com/item?id=42105171</a></p>
<p>Points: 4</p>
<p># Comments: 1</p>
]]></description><pubDate>Mon, 11 Nov 2024 07:32:26 +0000</pubDate><link>https://soniclm.com</link><dc:creator>ssmaameri</dc:creator><comments>https://news.ycombinator.com/item?id=42105171</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=42105171</guid></item><item><title><![CDATA[New comment by ssmaameri in "Free Local Text to Speech?"]]></title><description><![CDATA[
<p>OpenAI Whisper model is open source and can be run locally. There is a "light" version also to help it run on lower resourced machines, e.g local machine perhaps</p>
]]></description><pubDate>Fri, 06 Sep 2024 13:44:41 +0000</pubDate><link>https://news.ycombinator.com/item?id=41466143</link><dc:creator>ssmaameri</dc:creator><comments>https://news.ycombinator.com/item?id=41466143</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41466143</guid></item><item><title><![CDATA[New comment by ssmaameri in "Show HN: Python package for working with LLM's over voice"]]></title><description><![CDATA[
<p>Have setup a python package that makes it easy to interact with LLMs over voice<p>You can set it up on local, and start interacting with LLMs via Microphone and Speaker.<p>The idea is to abstract away the speech-to-text and text-to-speech parts, so you can focus on just the LLM/Agent/RAG application logic. And it does not tie you down to any specific LLM model or implementation. i.e you can use it to build simple or complex applications using the tech stacks of your choice<p>Currently it is using AssemblyAI for speech-to-text and ElevenLabs for text-to-speech, though that is easy enough to make configurable in the future<p>I just kickstarted this off as a fun project after working a bit with Vapi<p>Has a few issues, and latency could defo be better. Could be good to look at some integrations/setups using frontend/browsers also.<p>Would be happy to put some more time into it if there is some interest from the community
Package is open source, and is available on GitHub and PyPI.</p>
]]></description><pubDate>Fri, 06 Sep 2024 07:09:06 +0000</pubDate><link>https://news.ycombinator.com/item?id=41463673</link><dc:creator>ssmaameri</dc:creator><comments>https://news.ycombinator.com/item?id=41463673</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41463673</guid></item><item><title><![CDATA[Show HN: Python package for working with LLM's over voice]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/smaameri/voiceagent">https://github.com/smaameri/voiceagent</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=41463672">https://news.ycombinator.com/item?id=41463672</a></p>
<p>Points: 1</p>
<p># Comments: 1</p>
]]></description><pubDate>Fri, 06 Sep 2024 07:09:06 +0000</pubDate><link>https://github.com/smaameri/voiceagent</link><dc:creator>ssmaameri</dc:creator><comments>https://news.ycombinator.com/item?id=41463672</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41463672</guid></item><item><title><![CDATA[New comment by ssmaameri in "Show HN: PHP Library for Working with LLM, Agents and RAG"]]></title><description><![CDATA[
<p>Hello All,<p>I kicked of a small PHP package, with the aim of making it easy to work with LLMs, Agents and RAG in PHP.<p>It's just got a single method/class just now :) (release fast!?)<p>Wondering if it is something that sound's interesting to the PHP community. Why should Python guys have all the fun!<p>Would be great to have some sign of interest, and even feature requests, to inspire me to put some more work into it. Have kicked off the package here on github, and it is available on packagist also.<p>Like I said, it currently just supports one action, which allows you to send a message to OpenAI Chat by doing<p>$chat = new ChatOpenAI(getenv('OPENAI_API_KEY'));
$response = $chat->sendMessage('Hello, world!');<p>I know there is the LLPhant library, but this could evolve to be something a little different, perhaps with its own benefits<p>Any feedback? Feature requests would be great too.<p>Thanks!<p>Sami</p>
]]></description><pubDate>Thu, 29 Aug 2024 04:39:13 +0000</pubDate><link>https://news.ycombinator.com/item?id=41387368</link><dc:creator>ssmaameri</dc:creator><comments>https://news.ycombinator.com/item?id=41387368</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41387368</guid></item><item><title><![CDATA[Show HN: PHP Library for Working with LLM, Agents and RAG]]></title><description><![CDATA[
<p>Article URL: <a href="https://github.com/smaameri/squad">https://github.com/smaameri/squad</a></p>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=41387367">https://news.ycombinator.com/item?id=41387367</a></p>
<p>Points: 4</p>
<p># Comments: 1</p>
]]></description><pubDate>Thu, 29 Aug 2024 04:39:13 +0000</pubDate><link>https://github.com/smaameri/squad</link><dc:creator>ssmaameri</dc:creator><comments>https://news.ycombinator.com/item?id=41387367</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=41387367</guid></item><item><title><![CDATA[Show HN: ChatGPT over WhatsApp Service]]></title><description><![CDATA[
<p>I connected the WhatsApp and ChatGPT APIs to allow you to connect and speak with ChatGPT over WhatsApp. Have called it ChatsApp. Simply add the number +1 689 267 3467 to your phones contact list, and start chatting with ChatGPT over WhatsApp.<p>Was pretty simple to build. Also had to buy a virtual number online to allow setting up a WhatsApp account with. The WhatsApp servers receive the message from the WhatsApp mobile application, which forward a webhook request to the application server I setup. The request gets forwarded to the ChatGPT API (i.e the OpenAI Chat API), and voila, you are now in conversation with ChatGPT<p>Interestingly, the ChatGPT API does not provide context recognition from previous conversations out of the box. That is something that needs to be built in manually. So currently, the ChatsApp service does not include the context recognition from previous conversations. Maybe something to look at building out in the future.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=35257806">https://news.ycombinator.com/item?id=35257806</a></p>
<p>Points: 6</p>
<p># Comments: 1</p>
]]></description><pubDate>Wed, 22 Mar 2023 07:13:20 +0000</pubDate><link>https://chatsapp.carrd.co</link><dc:creator>ssmaameri</dc:creator><comments>https://news.ycombinator.com/item?id=35257806</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=35257806</guid></item><item><title><![CDATA[Show HN: AI Avatar Image Generator Based on Other AI Images]]></title><description><![CDATA[
<p>An AI Avatar image generator that creates images of you based on other AI created images.<p>The popularity of the recent AI Avatar image generator apps sparked some interest of mine in the area.<p>After playing around with a few AI Avatar image generators, some of which generate pictures of you based on pictures you upload and prompts you write, I thought, wouldn't it be much easier, instead of writing out prompts, to just select another image which you want your generated image to be based on.<p>The image the user selects is actually another AI generated image, so we know the prompt used to generate it. So prompt writing is abstracted away from the user, and instead they can search for images and click on ones they like.<p>Backend of the application currently uses Astria AI for the image model training and generation, and uses the Lexica API for getting lists of AI generated images and their prompts.</p>
<hr>
<p>Comments URL: <a href="https://news.ycombinator.com/item?id=34000315">https://news.ycombinator.com/item?id=34000315</a></p>
<p>Points: 5</p>
<p># Comments: 0</p>
]]></description><pubDate>Thu, 15 Dec 2022 14:49:22 +0000</pubDate><link>https://alterego-ai.com/</link><dc:creator>ssmaameri</dc:creator><comments>https://news.ycombinator.com/item?id=34000315</comments><guid isPermaLink="false">https://news.ycombinator.com/item?id=34000315</guid></item></channel></rss>