not an api but, Internally we’re just looking for a native text to speach app that auto records all meetings and call a webhook with the transcript. not the notes! for some reason all most rmeetings apps gives you only notes and seldomly a webhook or similar. also not interested in zapier etc.
After two weeks off looking for a solution, we’re going to vibe code something basic and use deepgram. If we just skipped the shopping around, the solution would be live already..
also check out Meeting BaaS (meeting bots as a service), we're an open-source competitor.
We thought long and hard of creating an SDK but did not go that route for now. Our main problem is that if you have to support Windows machines you're putting the finger into something really complicated.
And then depend on the end user's specs, etc.
So I'm really curious, in your case are you planning on deploying to Apple machines (m1+)? Or also set it up on Windows machines?
This, and there are also 3rd party bots that work with Teams (and presumably other video chats as well) that will join the meeting and do their own transcription. I've seen a couple of on meetings with vendors lately, it'll join and be called something like x company transcription bot.
I’ve checked out about 5 of them, I like krisp.ai the best, really nice native experience on mac. We do a lot of team meetings in discord channels. Almost none of them support discord and krisp allows for discord and in person recording. However no webhook in krisp, as team admin, i dont want to have every user configure a zapier integration to get the notes out. then pay for zapier also.
Only read.ai has webhook support, but all these tools only post notes to integrations. we want the full transcript to generate extract of what we think is important.
If you're looking for webhook support plus full transcript access (not just summarized notes), I'd recommend checking out ChatterBox as an alternative to Recall, but no sales call to start using, self-service, and less expensive (consumption model .09/hr). It supports real-time transcription and meeting data across platforms—including Zoom, Meet, and Teams. I don't believe they have a Discord or Slack integration, but it's built with developers in mind - I'd bet they'd explore it.
Many meetings happen that are not on teams.. So that would only do for 10%.. Id like to meet the teams where they are working instead of telling them to change how they work.
I'm pretty sure bots already exist for this, I've seen them join, albeit Teams, meetings that I've been on, so they can get a transcription of meetings where they don't control the host settings.
I was working on a work based STT system (I assume that's what you meant, not text tk speech) but might have to add in a webhook as well. What's the use case you need it for, just storing the transcripts somewhere?
We want to process the transcript to build up project context. Making it easy for team members and customers to ask project questions and brainstorm ideas with a chatbot
Interesting, I'm working on that exact type of use case on the consumer side as more of a mobile app chatbot, didn't realize there was an enterprise version need too of the same idea.
After two weeks off looking for a solution, we’re going to vibe code something basic and use deepgram. If we just skipped the shopping around, the solution would be live already..