Why I'm Building Another AI Meeting Notes Tool Instead of Using Granola.ai
Article URL: https://www.indiehackers.com/post/why-i-m-building-another-ai-meeting-notes-tool-C3yZAdu9r4DKF2B0zBI8 Comments URL: https://news.ycombinator.com/item?id=47612681 Points: 2 # Comments: 2
Everyone told me Granola was the answer.
Bot-free transcription, clean AI summaries, no interruptions. I installed it, opened it, and got this:
"Sign in with your Google Workspace account."
I have a personal Gmail only. That was the end of that.
I'm not complaining about Granola — it's a genuinely good product. But it's built for a specific person: someone inside a US/EU company, on a corporate Google or Microsoft account, doing meetings in English.
That's not most of the world.
The tools I tried either required a work account to unlock basic features, produced garbage transcripts the moment someone switched to Spanish or Portuguese, or trapped my notes inside their app with no real way out.
That last one frustrated me more than anything. After an hour-long call, you want your notes somewhere useful — in Notion, in a doc you send to a client, in your own folder. Not locked behind a share link in someone else's platform.
So I built CallBro.ai
The rules were simple:
Any email works. Personal Gmail, Outlook, a random address — doesn't matter. No workspace account, no calendar integration required unless you want it.
It has to work in Spanish, Portuguese, and other languages as well as it does in English. Not "we support 14 languages" in fine print while the AI summaries are clearly written for an English meeting. Actually work.
Export has to be real. Markdown, DOCX, PDF — take your notes and go. No lock-in.
And like Granola, no bot joins your call. CallBro captures audio at the system level. Nobody gets a "CallBro is recording this meeting" notification. The conversation stays natural.
It's still early. Windows support is coming. There's a lot left to build.
But if you're a freelancer, a founder doing international calls, a consultant who works in multiple languages — or just someone who doesn't have a corporate Google account — give it a try. Free to start, no card required.
I'd genuinely love to hear if this solves the same problem for you that it solved for me.
Hacker News AI Top
https://www.indiehackers.com/post/why-i-m-building-another-ai-meeting-notes-tool-C3yZAdu9r4DKF2B0zBI8Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Products
We Built a Robotics Developer Platform from Scratch - Meet Isaac Monitor & Robosynx
We Built a Full Robotics Developer Platform from Scratch — AI Generator, ROS 2 Architect, Physics Validator, Isaac Monitor, and More One platform that removes every single friction point between a robotics engineer and a working simulation — from generating your first robot file to monitoring a GPU training cluster in real time. This is Robosynx. The Problem We Set Out to Solve Robotics development in 2025 is powerful — but the tooling around it is still fragile, tribal, and painful. You want to test a new robot in NVIDIA Isaac Sim? You need to write URDF XML by hand. You want to move that robot to Isaac Lab for reinforcement learning? Now you need MJCF format, so you spend three hours refactoring XML. You want to validate that the physics won't explode your simulation? There's no standard
Qodo Merge Review: Is AI PR Review Worth It?
Quick Verdict Qodo Merge is one of the most feature-rich AI pull request review tools available in 2026, and the only major option backed by a fully open-source core. Built on the PR-Agent engine, Qodo Merge automatically generates PR descriptions, posts structured review comments, suggests code improvements, and identifies test coverage gaps - all within minutes of a pull request being opened. The February 2026 release of Qodo 2.0 introduced a multi-agent review architecture that achieved the highest F1 score (60.1%) among eight leading AI code review tools in comparative benchmarks. The open-source angle is what makes Qodo Merge genuinely interesting. You can self-host PR-Agent for free with your own LLM API keys and get the core review experience without paying a subscription. The manag
Everyone's Building AI Agents. Nobody's Building What Makes Them Work.
Three things happened this week. They tell the same story. On April 3, NPR reported that AI legal sanctions have hit 1,200+ cases , with a record fine of $110,000. Courts sanctioned ten cases in a single day. On April 4, The Week published that enterprise environments are still not ready for agentic AI —85% of companies want to deploy agents within three years, but 76% admit their operations can't support it. 50% of deployed agents operate in total isolation. This morning, NVIDIA launched an open agent platform, partnering with Salesforce, Adobe, Atlassian, and ServiceNow. The gold rush is accelerating. The narrative is seductive: AI agents are coming. Build them. Deploy them. Win. But the data tells a different story. The problem isn't the agents themselves. It's the infrastructure undern
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!