Bolna – build and ship enterprise grade voice AI in minutes
Hi Hacker News! This is Maitreya, Marmik and Prateek, co-founders of Bolna (https://github.com/bolna-ai/bolna). With Bolna, developers can create end-to-end conversational voice agents. They can connect to their own custom LLMs, their own Telephony, their own models etc. and create application features requiring voice AI. Here’s a small video: https://github.com/bolna-ai/bolna/assets/1313096/2237f64f-1c.... Our product originates from building an AI interviewer bot which can be used for practising coding interviews like Leetcode. By…
What it does
In the maker’s words, at launch
Hi Hacker News! This is Maitreya, Marmik and Prateek, co-founders of Bolna (https://github.com/bolna-ai/bolna). With Bolna, developers can create end-to-end conversational voice agents. They can connect to their own custom LLMs, their own Telephony, their own models etc. and create application features requiring voice AI. Here’s a small video: https://github.com/bolna-ai/bolna/assets/1313096/2237f64f-1c.... Our product originates from building an AI interviewer bot which can be used for practising coding interviews like Leetcode. By trying to build something like that, we realized that the orchestration layer can be a real pain point and hence something that everyone might want to use and build upon for any Voice AI feature. The hypothesis quickly got verified with the immense usage. We started off as a complete open source solution but quickly realized that to enable and expediate adoption and usage, we will need to create APIs on top of it so developers find it very very easy to use it. Hence, our package is wrapped over by an API layer which can be extended. Our primary focus has been to provide reliability towards latency and successful conversations. Our github repo https://github.com/bolna-ai/bolna has maintained a 30% fork:star ratio which is pretty massive from our point of view. We've seen developers fork us and try to build their own layers, their own telephony components, their own custom LLMs and models, etc. Later on we also released our hosted APIs for developers who wanted to use our managed hosted solutions - https://docs.bolna.dev/introduction and built a no-code/low-code playground for trying it out - https://playground.bolna.dev with a "chat" option to tune & test prompts since we realized that prompt is a very critical part for conversations to succeed. We recently released a complete open source end-to-end stack combining Whisper + Llama + MeloTTS (https://github.com/bolna-ai/bolna/tree/master/examples/whisp...) and hosted it's dockerized versions as well (still WIP) on docker hub. We think Bolna is quite unique since it encapsulates the underlying orchestration into API-able structure enabling developers to get started quickly via Docker, etc. I've been a great lover (and user) of the Elastic stack since 1.3x versions (circa. 2014) and trying to use a lot of inspiration from their open source process and philosophy on how to improve the adoption and usage. If this sounds interesting to you, please check us out! You can check us out our open source github repository at Github - https://github.com/bolna-ai or our hosted no-code/low-code dashboard at - https://playground.bolna.dev. We’d really love to hear your feedback and look forward to all of the comments!
Does a similar job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 19d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, August 2024
the whole month →
- IY
Life & fun · 2024 · ytch.xyz
- IA
Hey there HN! We’re Joe and Stopa, and today we’re open sourcing InstantDB, a client-side database that makes it easy to build real-time and collaborative apps like Notion and Figma. Building modern apps these days involves a lot of schleps. For a basic CRUD app you need to spin up servers, wire up endpoints, integrate auth, add permissions, and then marshal data from the backend to the frontend and back again. If you want to deliver a buttery smooth user experience, you’ll need to add optimistic updates and rollbacks. We do these steps over and over for every feature we build, which can…
Dev tools · 2024 · github.com