Product Catalog
464 products tracked
Speko
Hi HN! I'm Bek, founder of Speko, a platform that finds an optimal combination of speech-to-text, LLM, and text-to-speech models, given your constraints, among all our public benchmarked options, and tells you why. Demo: https://www.youtube.com/watch?v=no2LY2gRh-c Typical production voice agent is an ensemble of three models: STT, an LLM, and TTS. Each of those layers offers a dozen credible vendors, and each month there are new models on the market. Almost everyone evaluates once, picks a stack of their choice, and never rechecks because switching from a vendor to another involves yet another integration and arguments about the numbers. The result is that you use voice agents running last quarter's models while better and cheaper options are available. Before founding Speko, I spent four years as cofounder and CTO building voice agents for enterprises across Asia in 10+ languages. Each time a new speech model would arrive, we repeated the same ritual: hire native-speaking raters, benchmark it against our existing stack, and update production if it improved. Speko turns this process into an API. A team running thousands of calls a day told us: "we can literally go to this dashboard, switch the model, and it will do it for us." How it works: you send a request with your optimization criteria (accuracy, latency, cost or balanced), language and region. The router filters to models which we measured for the given combination of constraints, benchmarks them, selects the winner, and returns a response with headers containing provider, model names, and the scores. The gateway prefetches signed session plans, so a new session dials the provider straight from memory; no control-plane round trip while a caller waits. Failover happens only during connection setup stage: if the provider refuses the connection attempt, we start connecting to the runners-up. Some of the customer stories: one founder came to us not knowing what to pick at all: he gave us his use case and now routes everything through the platform. A property management AI runs LiveKit in Python and had not updated STT or TTS since launch: they did not know their STT had high error rates on their calls, better options existed, and swapping always looked like an R&D project. One team did not know which models to pick for Spanish. A medical team did not know which STT handles medical vocabulary best. In every case we helped find the right stack from the benchmarks, and now they route through us. The measuring part is public: we pass the same inputs to every model in one region in different dated runs and we publish the boards, including those where our selections perform worse than alternatives. A launch demo answers which 30-second clip sounds better; production asks which model survives minute eight, so we test spontaneous speech, money and dates, ten-minute takes, and the rankings change. We trained an automatic scorer for TTS naturalness on our blind head-to-head listening votes; on providers it has never seen a vote for, it picks the same winner our raters do about as often as raters agree with each other. We don't train or sell models ourselves, that's precisely how we keep our rankings impartial. We also open sourced the gateway for teams who want to avoid an extra network hop on the audio path and don't want to share keys with our cloud (https://github.com/SpekoAI/gateway, MIT): one Go binary, which is running as a sidecar in your agent's container, speaks one local protocol over Unix socket, pins provider hosts and attaches your keys. In BYOK mode it doesn't communicate with us at all. Notice that the anonymous, content-free telemetry is enabled by default, and one env var disables it. Cost: the gateway and BYOK setup will be free forever, we charge for the hosted router and managed keys with consolidated billing. Since we started the batch in late June, external usage has grown about 25 percent per week on average, front-loaded toward the launch weeks. I would love feedback from the community: how do you pick speech models now, and what makes you trust the third-party benchmark? https://speko.ai/
All roads lead home
I was a bit concerned when Google was sending comms about decommissioning Timeline on web. Then they did a mobile migration, and lost a bunch of user info. Started this app so I can always have a copy of my timeline on my icloud + server + device (3,2,1 rule) Hope y'all are able to find some value in it as well! BTW here is all the streets I've walked in NYC in the past 10 years: https://share.takeallroads.com/s/0Hq7jYxhS698Xyip-r4Prg (video version: https://imgur.com/a/e8p9aXt)
LLMs each trading $100K vs. a frozen rulebook
Show HN: LLMs each trading $100K vs. a frozen rulebook – the rulebook leads
Saggar, a Mac terminal that keeps sessions and your attention organized
Hi HN, like many of you talented folk, I’ve been building more, faster than ever. I built Saggar after my terminal stopped feeling like a tool and started feeling like a tab-management problem. Let me know you think!
1667, a terminal UI for writing fiction with language models
Hi HN. I built 1667 for my own fiction work and now use it each day. This probably has a limited audience. Maybe an audience of one... Why a terminal interface for story writing? I'm a dev. I like to use terminals for a lot of stuff. Most WebUIs feel off to me. That's the only reason. One thing that bothers me about writing in existing tools is that they don't fit the way I write. The mental model of my story is a tree. I try many takes usually continue with just one, but sometimes I want to try an alternate route and see where this goes. And that can branch again in many places. See what happens if I kill off this character or they don't take the job or whatever. 1667 is a full-screen terminal app for long-form fiction. Each story part can have several takes. All takes stay in a tree. You select one path through that tree as the story line. Export writes that line to Markdown in the project folder. Some technical details: - A project stores its stories and settings in a `.1667/` directory. Exported Markdown sits beside it. - Provider secrets stay in private machine files. Requests go to the provider that the writer selects. - An optional Vault Password seals project files at rest. - An operating-system lock permits one writer process for each project. - The request viewer shows the next provider request without its credential. - Each generated take keeps a Generation Record with its model and effective settings. Version 0.9.5 runs on macOS, Linux, and Windows x64. The website has Shell and PowerShell installers. An npm package is also available. 1667 imports Markdown, SillyTavern chats and cards, and NovelAI archives. It can use OpenAI-compatible, Anthropic, and local endpoints such as Ollama, LM Studio, llama.cpp, and KoboldCpp. Current limits: the release is pre-1.0. The interface is a terminal. There is no account or cloud sync, and I don't plan to add any. No tracking.
Desktopcolors.com
Hi HN, in my last vacation, I built desktopcolors.com as a place to collect iconic solid background colors. Let me know what you think.
Interactive component to map fibre breaks (OTDR)
Added an OTDR trace component as the latest in my component library for datacentre/network apps. Mainly for my own use in rackout.
Wordle for Metro Stations
One station to find per day, 2 or 3 gamemodes depending on the city (if your city is not live yet, or you can't find it in the selector, try https://dailymetro.live/cityname/mode/classic ) Like https://dailymetro.live/sf/mode/classic for San Francisco Got huge traction in France, so I thought maybe you'll like it here too :) Made with Claude code but still took at least 50-100h of dev/design/taking user feedbacks ahahah Hope you like it
A public AI whose memory is shared across all users
Show HN: A public AI whose memory is shared across all users
I built a native app for coding agents with Rust and GPUI
Show HN: I built a native app for coding agents with Rust and GPUI
Mic Drop, a real-time multiplayer karaoke game
Show HN: Mic Drop, a real-time multiplayer karaoke game
I evaluated file, vector, graph and RL based memory frameworks
Show HN: I evaluated file, vector, graph and RL based memory frameworks