Enabling end-to-end LLM-based voice driven conversational applications
Hey everyone on HN! We recently spent the past couple of weeks building out an end-to-end platform which can plug-in multiple models (both open/closed-source) to create voice driven conversational applications. We've tried to make the process simple & concise through documentation. Feel free to try it out and provide feedback. We will be launching a dashboard in the coming week for monitoring and analytics alongwith more open source models. Let us know what you all think. (if you want to contribute, we have tons of features planned - do let us know)
Enabling end-to-end LLM-based voice driven conversational applications launched on December 13, 2023 with 5 votes, #1,426 of 3,780 launches that month and more than 50% of that year's launches. The site was still online in September 2026, 2 years on.
What it does
Conversational voice AI agents. Contribute to bolna-ai/bolna development by creating an account on GitHub.
Does a similar job
all alternatives →
Conversational Replicas by Tavus2024 · tavus.io · ▲694Hey there, I’m Brian. I've been shipping conversational models over here at Tavus for the past two years. I want to tell you about our new audio-understanding model: Sparrow-2! It’s a new category of model and a unique new approach to conversational audio. Earlier this year we launched Sparrow-1, (at the time) our SoTA turn taking model. Since our Sparrow-1 launch, I’ve spent a lot of time listening to humans talking and trying to really understand how people know when to talk, when to listen, and when to wait. I’ve also been hunting down failure modes of the current SoTA models. And while…
I built a sub-500ms latency voice agent from scratchMar 2026 · ntik.me · ▲570I built a voice agent from scratch that averages ~400ms end-to-end latency (phone stop → first syllable). That’s with full STT → LLM → TTS in the loop, clean barge-ins, and no precomputed responses. What moved the needle: Voice is a turn-taking problem, not a transcription problem. VAD alone fails; you need semantic end-of-turn detection. The system reduces to one loop: speaking vs listening. The two transitions - cancel instantly on barge-in, respond instantly on end-of-turn - define the experience. STT → LLM → TTS must stream. Sequential pipelines are dead on arrival for natural…
- IBI built a non-linear UI for ChatGPT2024 · grafychat.com · ▲459
Hi HN, I built this out of frustration of the evergrowing list of AI models and features to try and to fit my workflow. The visual approach clicks for me so i went with it, it provides more freedom and control of the outcome, because predictable results and increased productivity is what I’m after when using conversational AI. The app is packed with features, my most used are prompt library, voice input and text search, narration is useful too. The app is local-first and works right in the browser, no sign up needed and it's absolutely free to try. BYOAK – bring your own API Keys. Let me…
Open-source, native audio turn detection model2025 · github.com · ▲126Our goal with this project is to build a completely open source, state of the art turn detection model that can be used in any voice AI application. I've been experimenting with LLM voice conversations since GPT-4 was first released. (There's a previous front page Show HN about Pipecat, the open source voice AI orchestration framework I work on. [1]) It's been almost two years, and for most of that time, I've been expecting that someone would "solve" turn detection. We all built initial, pretty good 80/20 versions of turn detection on top of VAD (voice activity detection) models. And…
Vogent Voicelab2025 · vogent.ai · ▲171Hi HN! Voicelab is an API for optimized inference of top open-source TTS models. CSM-1B and Orpheus are the currently supported models, but we’re adding Dia, Chatterbox, Kokoro, and more in the next couple of weeks. While new ultra-realistic open-source voice models come out every month, most people still use one of a couple of closed-source providers. The reason is that these research previews can lack production-readiness; their inference stacks are usually not amenable to running things scalably (i.e. only one concurrent stream per GPU), and the public weights can generate speech of…
- RTReal-time voice chat with AI, no transcription2024 · demo.tincans.ai · ▲33
Hi HN -- voice chat with AI is very popular these days, especially with YC startups (https://twitter.com/k7agar/status/1769078697661804795). The current approaches all do a cascaded approach, with audio -> transcription -> language model -> text synthesis. This approach is easy to get started with, but requires lots of complexity and has a few glaring limitations. Most notably, transcription is slow, is lossy and any error propagates to the rest of the system, cannot capture emotional affect, is often not robust to code-switching/accents, and more. Instead, what…
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 21d ago · stillwet.art
FastRouter.ai▲364Route requests to the right LLM for cost, latency & quality
AI · 22d ago · fastrouter.ai
Source: Show HN post ↗
Launched alongside, December 2023
the whole month →
Hi HN! I’m proud to share that we have built a real 3rd party iMessage client for Android. We did it by reverse engineering the iMessage protocol and encryption system. It's available to download today (no waitlist): https://play.google.com/store/apps/details?id=com.beeper.ima and there's a technical writeup here: https://blog.beeper.com/p/how-beeper-mini-works. Unlike every other attempt to build an iMessage app for Android (including our first gen app), Beeper Mini does not use a Mac server relay in the cloud. The app connects directly to Apple…
Work · 2023 · beeper.com
Hey! I made Heynote entirely for my own use case. For many years, I always had an Emacs instance running with the scratch buffer open, even long after I had abandoned Emacs as my programming editor in favor of more recent IDE:s. The simplicity of having just one big scratch buffer appeals to me, but I still want to separate the different things I jot down somehow (without using tabs or similar). Previously, my solution was to insert a bunch of blank lines between the notes, but hitting C-A would still select the entire buffer. That's why I came up with the concept of "blocks", which turned…
Work · 2023 · heynote.com
FuseBase▲939Client collaboration platform for professional services
Dev tools · 2023 · thefusebase.com
Beep! 2.0▲871Fastest tool to assign and share visual tasks with your team
Work · 2023 · justbeepit.com
Inbox Zero▲821Clean Up Your Inbox In Minutes Newsletter management, AI automation, and email analytics. Inbox Zero is the open-source email app that puts you back in control of your inbox.
AI · 2023 · getinboxzero.com