Launch HN: Recall.ai (YC W20) – API for meeting recordings and transcripts
Hey HN, we're David and Amanda from Recall.ai (https://www.recall.ai). Today we’re launching our Desktop Recording SDK, a way to get meeting data without a bot in the meeting: https://www.recall.ai/product/desktop-recording-sdk. It’s our biggest release in quite a while so we thought we’d finally do our Launch HN :)Here’s a demo that shows it producing a transcript from a meeting, followed by examples in code: https://www.youtube.com/watch?v=4croAGGiKTA . API docs are at https://docs.recall.ai/.Back in W20, our first product was an API that lets you send a bot participant into a meeting. This gives developers access to audio/video streams and other data in the meeting. Today, this API powers most of the meeting recording products on the market.Recently, meeting recording through a desktop form factor instead of a bot has become popular. Many products like Notion and ChatGPT have added desktop recording functionality, and LLMs have made it easier to work with unstructured transcripts. But it’s actually hard to reliably record meetings at scale with a desktop app, and most developers who want to add recording functionality don’t want to build all this infrastructure.Doing a basic recording with just the microphone and system audio is fairly straightforward since you can just use the system APIs. But it gets a lot harder when you want to capture speaker names, produce a video recording, get real-time data, or run this in production at large scale:- Capturing speaker names involves using accessibility APIs to screen-scrape the video conference window to monitor who is speaking at what time. When video conferencing platforms change their UI, we must ship a change immediately, so this keeps working.- Producing a video recording that is clean, and doesn’t capture the video conferencing platform UI involves detecting the participant tiles, cropping them out, and compositing them together into a clean video recording.- Because the desktop recording code runs on end-user machines, we need to make it as efficient as possible. This means writing highly platform-optimized code, taking advantage of hardware encoders when available, and spending a lot of time doing profiling and performance testing.Meeting recording has zero margin for failure because if anything breaks, you lose the data forever. Reliability is especially important, which dramatically increases the amount of engineering effort required.Our Desktop Recording SDK takes care of all this and lets developers build meeting recording features into their desktop apps, so they can record both video conferences and in-person meetings without a bot.We built Recall.ai because we experienced this problem ourselves. At our first startup, we built a tool for product managers that included a meeting recording feature. 70% of our engineering time was taken up by just this feature! We ended up starting Recall.ai to solve this instead. Since then, over 2000 companies use us to power their recording features, e.g. Hubspot for sales call recording, Clickup for their AI note taker. Our users are engineering teams building commercial products for financial services, telehealth, incident management, sales, interviewing, and more. We also power internal tooling for large enterprises.Running this sort of infrastructure has led to unexpected technical challenges! For example, we had to debug a 1 in 36 million segfault in our audio encoder (https://www.recall.ai/blog/debugging-a-1-in-36-000-000-segfa...), we encountered a Postgres lock-up that only occurs when you have tens of thousands of concurrent writers (https://news.ycombinator.com/item?id=44490510), and we saved over $1M a year on AWS by optimizing the way we shuffle data around between our processes (https://news.ycombinator.com/item?id=42067275).You can try it here: https://www.recall.ai. It's self-serve with $5 of free credits. Pricing starts at $0.70 for every hour of recording, prorated to the second. We offer volume discounts with scale.All data recorded through Recall.ai is the property of our customers, we support 0-day retention, and we don’t train models on customer data.We would love your feedback!
59 points by davidgu - 29 comments
I'm curious given your decision to capture speaker names from the screen. I see the merits during desktop recording, but I can also see how this limits utility when trying to offer the same functionality across desktop and other scenarios (e.g. in-person meetings, audio uploads etc.)
For in-person meetings and audio uploads, this is on our roadmap and in development. More to come on this!
Recall is, at its core, an API for bot recording. As someone building an application that relies heavily on conversational data, recording meetings is really important. Recall makes that process as easy as an API call, standardized across various meeting platforms. It's a huge PITA to set up infrastructure to get bots to join meetings that handle each platforms' proclivities, encoding and storing video data, etc.
The transcription service is just something they do to make transcribing recordings - one of the most common first post-processing steps for any conversational data - easier and lower friction.
I actually agree that it’s become incredibly easy to transcribe conversations using open-source models, and that’s not where Recall adds the most value. The hard part is building the infrastructure that allows you to get real-time access to the raw audio, video, and transcript data directly from the meeting platforms. We abstract all of that away and provide you with a clean interface to access that data. Once you get the data, you could use any of the models that you mentioned to do your own transcription, or transcribe using Recall’s transcription models.
Where we come in is for companies building products that need to support all of their customers across Zoom, Meet, Teams, Webex, etc. Most enterprises don’t want five different integrations, and native APIs often come with restrictions (like only the organizer being able to access the file, or recordings not being available until after the call).
No but seriously, y'all have built not only an incredible product that I had the chance to demo, but a great company as well, through your previous pivots and cofounder changes. You're building schlep tools that product companies _definitely_ don't want to do, years before it was clear there was a market here, and do it well.
There's definitely demand for a native screen recorder, and I think it's the right move to be agnostic to privacy (the lower down the stack you go, the more permissable you should be about use-cases). Imagine how much competition in file storage there would have been had there been an API provider for Dropbox's Finder sync technology (though you could argue it just incentivizes large companies like Hubspot to build their own screen recording feature into their platform, rather than enabling new startups like Gong but I digress).
Y'all deserve the success that you have, and wishing you all the best of luck with the new product launch!
Both why send it and why send it with very little info included on the page?
Modern LLMs can power sales coaching, medical scribing, legal review, support QA, and compliance reporting but they need consistent inputs to process. We handle capture/formatting/edge cases so developers can focus on models and UX
Congrats on the launch! :tada:
Because consent laws are complex and vary by region and industry, we leave the consent flow to the developer and we provide the tools and guidance to do it correctly. As with our Meeting Bot API, we also urge teams to follow local laws and make recording clearly visible to users
Consult Linda Tripp
I run an open source alternative to Recall (for meeting bots), and our costs are about 8 cents per hour.
Instead, we built a single API that can get the same results without the issues mentioned above so you can focus on building the features your users care about