Show HN: Voice bots with 500ms response times https://ift.tt/NVmnpij

Show HN: Voice bots with 500ms response times Last year when GPT-4 was released I started making lots of little voice + LLM experiments. Voice interfaces are fun; there are several interesting new problem spaces to explore. I'm convinced that voice is going to be a bigger and bigger part of how we all interact with generative AI. But one thing that's hard, today, is building voice bots that respond as quickly as humans do in conversation. A 500ms voice-to-voice response time is just barely possible with today's AI models. You can get down to 500ms if you: host transcription, LLM inference, and voice generation all together in one place; are careful about how you route and pipeline all the data; and the gods of both wifi and vram caching smile on you. Here's a demo of a 500ms-capable voice bot, plus a container you can deploy to run it yourself on an A10/A100/H100 if you want to: https://ift.tt/m0upwDI We've been collecting lots of metrics. Here are typical numbers (in milliseconds) for all the easily measurable parts of the voice-to-voice response cycle. macOS mic input 40 opus encoding 30 network stack and transit 10 packet handling 2 jitter buffer 40 opus decoding 30 transcription and endpointing 200 llm ttfb 100 sentence aggregation 100 tts ttfb 80 opus encoding 30 packet handling 2 network stack and transit 10 jitter buffer 40 opus decoding 30 macOS speaker output 15 ---------------------------------- total ms 759 Everything in AI is changing all the time. LLMs with native audio input and output capabilities will likely make it easier to build fast-responding voice bots soon. But for the moment, I think this is the fastest possible approach/tech stack. https://ift.tt/m0upwDI June 27, 2024 at 03:21AM

Show HN: Quick Rewire – Test your brain's neuroplasticity https://ift.tt/vNxftKr

Show HN: Quick Rewire – Test your brain's neuroplasticity Hey HN, this is a game to test your brain's neuroplasticity. It tests how fast your brain adapts and rewires. It doesn't work with mobile browsers. https://ift.tt/U8Hv2Fm June 27, 2024 at 02:33AM

Show HN: I built a static site builder https://ift.tt/DyVld21

Show HN: I built a static site builder https://ift.tt/7id3QtR June 25, 2024 at 11:38PM

Show HN: From dotenv to dotenvx – better config management https://ift.tt/mjSLM8a

Show HN: From dotenv to dotenvx – better config management https://ift.tt/AzHTRCg June 25, 2024 at 08:19PM

Show HN: The Tomb of Nefertari [QV 66] Guided Virtual Tour https://ift.tt/0WxidSl

Show HN: The Tomb of Nefertari [QV 66] Guided Virtual Tour I 3d scanned the Tomb of Nefertari and am building this guided virtual tour, trying to bring in photogrammetry of artifacts that I've made at various museums. It crashes sometimes still on mobile devices. I wasn't able to take photogrammetry photos of the artifacts from the tomb in the Museo Egizio in Turin because they were traveling while I was there (and now the museum is closed to install a new roof anyhow), so I tried to include comparanda from other museums where I had scanned artifacts. I tested the same dataset with 3d Gaussian Splatting but that had lower resolution results for great complexity in frontend code and reduced performance on older devices. [3DGS tour: https://ift.tt/o49Qe5k... ] Moving forward, if anyone's working on the same idea, I didn't find a good path to monetization through web-based 3d content, so I'll take the high resolution photogrammetry of spaces into Unreal and switch to desktop and headset builds. For the distribution advantage of web-based 3d content, I'm hoping to test next a desktop or VR build that may be easier to sell to sustain my work. https://ift.tt/PHCjRZ5 June 25, 2024 at 08:18PM

Show HN: I made a remote job board with a free CV maker tool https://ift.tt/CP0wpb6

Show HN: I made a remote job board with a free CV maker tool https://benture.io/ June 25, 2024 at 02:27PM

Show HN: AI-Generated Tables for a Steampunk City https://ift.tt/owerQUi

Show HN: AI-Generated Tables for a Steampunk City I recently embarked on a creative experiment where I used ChatGPT to craft an elaborate steampunk story. Inspired by the rich narrative and intricate details, I decided to transform various parts of the story into demo tables, complete with text and images using https://tabulator.ai/ . The goal was to explore how AI can aid in the creative process and provide indie game developers and storytellers with some ideas quickly. https://ift.tt/YVoyztZ June 25, 2024 at 02:34PM

Show HN: Qq: like jq, but can transcode between many formats https://ift.tt/yWxak5H

Show HN: Qq: like jq, but can transcode between many formats qq is jq inspired interoperable config format transcoder with interactive querying. It features an optional interactive editor with autocomplete for structured data. And supports inputs and outputs for json, xml, ini, toml, yaml, hcl, tf, and csv to varying degrees of capability. https://ift.tt/eKrM4b2 June 25, 2024 at 04:14AM

Show HN: Sandcastle – a minimal, lightweight build tool and shell automator https://ift.tt/6obwa0H

Show HN: Sandcastle – a minimal, lightweight build tool and shell automator Automate your repetitive build tasks and terminal commands with Sandcastle. Built in Go. I'm a solo student developer - I'm open to contribution to build this into something that everyone can and will want to use. https://ift.tt/rDRqVZy June 25, 2024 at 12:16AM

Show HN: Field report with Claude 3.5 – Making a screen time goal tracker https://ift.tt/ENlwHRI

Show HN: Field report with Claude 3.5 – Making a screen time goal tracker https://ift.tt/1wx9ac4 June 24, 2024 at 07:00AM

Show HN: API for Internet Brand Data https://ift.tt/uPDEzej

Show HN: API for Internet Brand Data https://brand.dev/ June 24, 2024 at 01:32AM

Show HN: Open-source version of Anthropic's Artifacts UI https://ift.tt/x7kz8lh

Show HN: Open-source version of Anthropic's Artifacts UI https://ift.tt/SQXEqkB June 24, 2024 at 03:51AM

Show HN: Tsellm: Interactive SQLite shell with LLM support https://ift.tt/OtiVC7s

Show HN: Tsellm: Interactive SQLite shell with LLM support Hello HN, While browsing the Python docs yesterday, I discovered that the latest 3.12 version has added support for a `python3 -m sqlite3` interactive shell. I looked into the source code, and its implementation was simple, giving me an idea: Why not hook the beautiful llm library by simonw into such an interactive shell, and thus have direct LLM support in SQLite? Without writing a C extension, build a shared object and all that fuss. Well, now you can `pip install tsellm` and do just that. demo gif: https://ift.tt/qNtvuWY... https://ift.tt/Cuf0gYy June 23, 2024 at 11:45PM

Show HN: Online OPML editor to manage subscription lists https://ift.tt/XBUnGqd

Show HN: Online OPML editor to manage subscription lists I made a small online editor to manage OPML[1] files easily. There are a lot of smart online editors for formats like JSON, but while OPML is supported by most subscriptions services, the experience of editing/managing it is poor outside of what each platform support. The pain of managing the file independently increases as the size of the OPML file grow larger. It's rather simple at the moment but the goal is to provide shortcuts for common desired tasks to make the experience of editing OPML much smoother and streamlined. The editor is a static website that runs locally in your browser, it doesn't require an account, nor do any tracking. Let me know your feedback or if you've any pain points around OPML GitHub repo: https://ift.tt/S541Yuq Website: https://ift.tt/Ixjdu3t [1] - https://ift.tt/InwgA64 https://ift.tt/S541Yuq June 21, 2024 at 06:43PM

Show HN: Simple script to cripple personalized targeting from Facebook https://ift.tt/ea3pYfw

Show HN: Simple script to cripple personalized targeting from Facebook https://ift.tt/R147BkA June 23, 2024 at 03:08AM

Show HN: Feedback on Sketch Colourisation https://ift.tt/sMmBAKv

Show HN: Feedback on Sketch Colourisation Hi I am looking for some feedback on our new project "Sketch Colourisation". The envisioned UI and objectives are -- * An artist should have greater control on how to colour a sketch. While a text-to-image model lacks this fine-grained control, a per-pixel colourisation pipeline makes sketch colourisation a laborious process with high-entry barrier. * What if an artist only draws a mask for a local region and specifies the colour palette for that local region? Then a neural network figures out how to colour the overall sketch -- while maintaining those local colour palette. [I would really like a feedback if the above UI (i.e., mask and local colour palette) makes sense to users/designers. As researchers, we often have the wrong idea of what is desired by end-users.] * On the exact implementation of the above concept, we designed a no-training based neural network framework -- and also make sure it runs on a Nvidia 4090. In other words, I will try to avoid any expensive training or inference -- which defeats the purpose of being useful to people (not just some research labs). * Note, I am not so bothered about the exact implementation (or whether it is "novel") -- as long as it is useful. * A shameless advertisement: The codebase ( https://ift.tt/1fM3RP5 ) is MIT License. It is no way near to being useful to people -- but I would really like to pursue this direction and your feedback/criticism will be immensely helpful. Thanks https://ift.tt/6lsANHg June 22, 2024 at 05:03PM

Show HN: I made tool that let's you see everything about any website https://ift.tt/mPwB2pQ

Show HN: I made tool that let's you see everything about any website Yes, it's open source: https://ift.tt/8seW9PU :) Why I'm building this? There are a lot of tools out there for discovering meta and security data relating to a website, IP or server. But currently, there isn't anything that does everything, all in one place and without a paywall/ user sign up. It's still a WIP, and I'm working on a new version, with some more comprehensive checks, so any feedback would be much appreciated :) https://v1.web-check.xyz/ June 22, 2024 at 04:13PM

Show HN: Synapse – TypeScript Toolchain for Cloud Apps https://ift.tt/nD6bd3X

Show HN: Synapse – TypeScript Toolchain for Cloud Apps Hey all, I've been working on a developer tool based on my experiences with working on cloud applications. What I've created is basically Node.js + TypeScript + Terraform all combined into a single tool, Synapse. I like to think of Synapse as a "compiler for distributed systems", though it can also be used as a build tool for any JavaScript/TypeScript app. In fact, Synapse is built with Synapse! I recently open-sourced the bulk of the codebase, but a lot of work is still needed to make it easy to contribute. If anyone is able to try it out and give me feedback, it would be hugely appreciated! There's not many documented features at the moment, but I think what I have now is at least enough to get a basic idea of what Synapse can do. https://ift.tt/sugi2IV June 22, 2024 at 03:51AM

SHOW HN: A tool to scale PDF files to a specific paper size, such as A2, B2 https://ift.tt/IYVubjP

SHOW HN: A tool to scale PDF files to a specific paper size, such as A2, B2 https://ift.tt/b7G8MP9 June 22, 2024 at 03:31AM

Show HN: We Added Full Schema Enforcement to a Document Database https://ift.tt/i7VN1Ba

Show HN: We Added Full Schema Enforcement to a Document Database https://ift.tt/GpXS09u June 20, 2024 at 11:08PM