bolna

low-code dashboard at - https://platform.bolna.ai. We’re inspired by open ecosystems like the Elastic stack and trying to follow a similar path: open by default, but easy to extend or host as needed.

uickly 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!

(useful for basic calls and really pocket friendly). Normal (<2sec latency but only one llm call means it's cheaper than nitro), Nitro (<1sec latency and but multiple llm calls means really expensive) 5. Follow up tasks like webhook integration, summarisation, and extraction. 6. Modular and extensible architecture, which means connecting two different llms yet parallel paths(for example code and english to automate leetcode screening interviews) is really easy, albeit you'll initially need some hacking until we're able to release that to both hosted and open source versions). 7. Vector and Scalar caches to reduce the entire cost (by 3x compared to deepgram + mixtral + elevenlabs) and latency by 300ms - 500ms. 8. Semantic routing Over the next weeks we'd be doing a lot of small releases here starting with a Speech language model only pipeline, integrating gazzele We'd love to welcome you guys to our community, give us feedback and together build "langchain for voice first AI assistants".