We do this at quillmeetings.com - the audio stays on your device and is transcribed by whisper. We also do speaker splitting and recognition with a combination of models. If you share or sync notes/meetings they are e2e encrypted.
FYI, the transcript-only product is free forever (it's local, so why not?), but generating AI notes, interpreting screenshots if you enable that, etc. are in the Pro plan and do require using a cloud API.
We did a lot of work at https://www.quillmeetings.com to build a diarization & speaker recognition pipeline that works locally on mac and windows. Basically, we can create embeddings of parts of the audio, like you might create embeddings for text for a RAG system, and cluster them (simplifying a lot of details from the "last 80%" that has taken a lot of effort to get working...)
The speaker recognition can't be as perfect as listening to each stream separately like Zoom itself can do, but it also learns your contacts over time and can recognize voices for ad-hoc in-person meetings, etc. which I've found really magical since we launched it.
Ah yes, a locally-run, mostly-accurate speaker recognition pipeline that isn't open source. Love to see cool features locked away while the rest of us plebs make do with whatever scraps the OSS world has managed to build. But hey, at least it kind of works, so you can enjoy your slightly-wrong diarization in private.
There's nowhere I'd rather work right now than AngelList - our motto in hiring is "Would I start a company with this person?", so all of my coworkers are amazing, skilled people.
Together, we're not just funding 40+ startups per month - we're connecting these startups to a diverse group of investors whom they can reach out to for advice, connections, etc. And for the investors, this is a 10X improvement over any other way to invest (https://t.co/7AmuxYWHe3).
Fundraising is a complex market with multiple sides, so we are looking for great engineers who are excited to tackle this problem and streamline the entire market.
Our other business is matching people to their next startup job. On AngelList Talent, we believe in transparency (all jobs have salary and equity ranges disclosed).
This model has led to tremendous growth, but we still have a lot to do. There's room here for any engineer or designer to have a huge impact on the next iteration of AngelList Talent and change the lives of thousands of your peers.
There's nowhere I'd rather work right now than AngelList - our motto in hiring is "Would I start a company with this person?", so all of my coworkers are amazing, skilled people.
Together, we're not just funding 40+ startups per month - we're connecting these startups to a diverse group of investors whom they can reach out to for advice, connections, etc. And for the investors, this is a 10X improvement over any other way to invest (https://t.co/7AmuxYWHe3).
Fundraising is a complex market with multiple sides, so we are looking for great engineers who are excited to tackle this problem and streamline the entire market.
Our other business is matching people to their next startup job. For jobs, we believe in transparency (all jobs have salary and equity ranges disclosed).
This model has led to tremendous growth, but we still have a lot to do. There's room here for any engineer or designer to have a huge impact on the next iteration of AngelList Talent and therefore change the lives of thousands of other engineers and designers.
Apply via AngelList and mention that you saw Mike's message on Hacker News.
We are a small team making a big impact. Naval and Nivi (and really, everyone on the team) have been involved with multiple startups and want to create a community where we can set founders and investors up for success. We’re looking for like-minded, full-stack engineers and designers to join our team.
To learn how we work, read up on our blog here: http://venturehacks.com/articles/1-man-startups
A few other words we live by:
• Ask forgiveness, not permission
• You break it, you bought it
• S/he who codes, rules
• Low inventory
• Be real
• Sweat the details and corner cases
• You must code
• Do what you think is right (and be right)
We are a small team making a big impact. Naval and Nivi (and really, everyone on the team) have been involved with multiple startups and want to create a community where we can set founders and investors up for success. We’re looking for like-minded, full-stack engineers and designers to join our team.
True, that is quite good inside the GFW. As a comparison, I am in Beijing in an apartment from 2002, with a DSL connection that China Unicom sells as 4Mbps (the best I could buy here):
I agree that it doesn't really sound like him, but the voice is far better than most Chinese computer voices that I've heard and is totally understandable.
Seems like my years of learning Chinese and living in China are about to become useless...
Actually I stopped learning Chinese and living in China because I discovered the following. They were learning English faster then I could learn Chinese, and I only needed to know enough to let them know I wasn't culturally insensitive.
Not sure where the quote was but it went along the lines of "Don't try to talk in their language, because you will make a hash of it and they will have the advantage."
FYI, the transcript-only product is free forever (it's local, so why not?), but generating AI notes, interpreting screenshots if you enable that, etc. are in the Pro plan and do require using a cloud API.