Product Thumbnail

Klang

Team memory of meetings and calls, on our own speech models

Privacy
Meetings
Artificial Intelligence
Visit WebsiteSee on Product HuntLinkedIn ⧉Github ⧉App Store ⧉Play Store ⧉MCP server ⧉

Hunted byAndreas ArgeliusAndreas Argelius

Klang is a memory of all your organisation's important conversations. Record meetings in the room, calls and online meetings with the iPhone and Android app, the Mac and Windows apps (beta) or the web. Klang connects them into one shared repository you can search, question and analyse, or open to your AI agents through MCP. Under the hood, we're an AI speech lab: we train our own speech models, like Pianissimo, our open model for Swedish and Danish. Built in Sweden. Free to start.

Top comment

Hi Product Hunt, I'm Andreas, co-founder and CTO of Klang.

Klang is a memory of all your important conversations, shared across your organisation instead of scattered in people's notes. Under the hood, we're an AI speech lab. Most large speech models are trained mainly on English, and other languages fall behind. So we train our own.

Our open model, Pianissimo, covers Swedish and Danish today. Norwegian is next, and more languages will follow. It transcribes an hour of audio in about a second on a single server GPU, and is small enough to run locally on an ordinary laptop. In our Danish tests it had the lowest error rate of the open and closed models we compared. The weights are open under CC BY 4.0, and our research is at research.klang.ai.

What Klang does today:

  • Records conversations where they happen. The iPhone and Android app records meetings in the room and phone calls. The desktop app for Mac and Windows, both in beta, records online meetings with no bot. Or the Klang assistant joins your calendar meetings.

  • Keeps transcripts, summaries and to-dos in one repository your team shares.

  • Answers questions across all of it, with sources you can check.

  • Runs scheduled analyses, like a weekly summary of sales call objections.

  • Opens your conversation memory to Claude, ChatGPT or your own agents through MCP, API and CLI.

Klang is built in Sweden and hosted in the EU. We're ISO 27001 certified, and we never train AI models on your conversations.

There's a free plan that doesn't expire. I'd love to hear where your important conversations get lost today, and which language you'd like us to train next.

Comment highlights

No comment highlights available yet. Please check back later!

About Klang on Product Hunt

“Team memory of meetings and calls, on our own speech models”

Klang launched on Product Hunt on November 12th, 2026 and earned 69 upvotes and 1 comments, placing #36 on the daily leaderboard. Klang is a memory of all your organisation's important conversations. Record meetings in the room, calls and online meetings with the iPhone and Android app, the Mac and Windows apps (beta) or the web. Klang connects them into one shared repository you can search, question and analyse, or open to your AI agents through MCP. Under the hood, we're an AI speech lab: we train our own speech models, like Pianissimo, our open model for Swedish and Danish. Built in Sweden. Free to start.

Klang was featured in Privacy (11.5k followers), Meetings (6.5k followers) and Artificial Intelligence (483.9k followers) on Product Hunt. Together, these topics include over 154.6k products, making this a competitive space to launch in.

Who hunted Klang?

Klang was hunted by Andreas Argelius. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.

Want to see how Klang stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.