Smart voice-to-text that turns messy, real-world speech into perfectly formatted text. Now, with Notetaker.

San Francisco, CA
If your workday runs on Outlook, we’ve got you covered. You can now connect your Outlook calendar to Notetaker and bring your meetings along.
2
16
1,605
Update: you can now write your Hinglish in English letters, the way you’d type it.
10
1
71
5,489
Your meeting context, now in Claude and ChatGPT. Connect Notetaker to pick up where your meeting left off and keep work moving forward.
7
6
135
13,668
we're hiring for 30+ roles across eng, marketing, gtm, and ops come build the future of HCI with us :) wisprflow.ai/careers
Pulled the fastest growing startups by hiring velocity over the past 90 days:
18
9
377
55,655
"let’s circle back on those Q4’s KPIs, ladder the OKRs into our B2B GTM flywheel, and synergize our ICP research to unblock H2 ARR goals by EOD." We don't know what that means either. But our dictionary does. Now, you can add your team's unique terms as shared vocabulary so nothing is missed.
4
32
5,469
Introducing Canto, our latest speech model for real-time dictation. On our evaluation of 9.8 hours of English Flow dictations from more than 2,300 speakers, Canto achieved a 3.4% word error rate—the lowest among the models we tested. Learn more about Canto from our CSO, Ariya Rastrow:
19
20
184
16,455
Your meeting context, now in Gemini. We’ve rolled out Wispr Flow Notetaker’s one-click MCP connection to Gemini. Bring your meeting notes straight into your Gemini workflows, all without copying and pasting.
8
8
100
12,094
Wispr Flow retweeted
Today is an exciting one: Notetaker is now live on Windows. When we launched Notetaker, I wrote about how much we hate messy meeting notes. We wanted something that gets the details right and makes it easy to push your work forward. That becomes especially useful a few meetings later. You’re writing a proposal and need to remember what the customer asked for. You’re planning next week and want to check which decisions are still open. The context you need is spread across several conversations. With Notetaker, you can ask questions across your recorded meetings and get answers with links back to the source. Your personal dictionary helps it recognize the names and terminology you use at work, making those conversations easier to follow when you come back to them. You can also bring that meeting context into your AI tool of choice, alongside the documents you’re already working with. A conversation with a customer can inform a proposal. A discussion with your team can become the starting point for a project plan. So much of our work starts with something someone said. We want that context to stay useful as the work develops, whether you’re following up that afternoon or revisiting a decision weeks later. A good conversation should keep being useful after the meeting ends, and that’s exactly why we’ve built Notetaker.
17
2
99
8,558
Notetaker is now live on Windows! When Friday rolls around and you’re trying to remember what came up in Monday’s meeting, just ask. Notetaker searches your recorded meetings and links you back to the conversation. You also have: - Accurate transcription in 20+ languages - A personal dictionary for the names and acronyms your team uses - Meeting context you can bring into Claude, ChatGPT, and Gemini Watch the walkthrough to see it in action👇
7
6
51
7,191
Wispr Flow retweeted
I sat down with Lance Martin from Anthropic, Mihir Garimella from Actively, and Todd Olson from Pendo to talk about what it actually takes to build agents that work in production. We covered how each of us thinks about evals, memory, cost, and the decision to build agent infrastructure yourself or rely on a managed system. Really enjoyed comparing notes with a group of people working through these questions in very different products. Thank you to the Anthropic team for bringing us together.
We sat down with the founders of @WisprFlow, @useactively, and @pendoio, who are building on Claude Managed Agents. Learn how they used features like outcomes, sandboxing, and memory to scale their products.
3
1
12
2,914
Wispr Flow retweeted
Using my foot for voice dictation Stream Deck pedal + DJI Mic Mini + Wispr Flow is the best set-up
42
7
238
17,098
This is no time for keyboards 🗣️
We’re introducing Claude Fable 5.1 and Claude Mythos 5.1. They're the world’s most advanced models for coding and knowledge work.
11
3
92
11,126
At Wispr Flow, we're building toward a future where interacting with devices is as seamless as talking to a friend. That vision has always gone beyond dictation. With Notetaker, we’re taking another step toward helping people do more simply by speaking. It turns conversations into a growing layer of context around your work, helping you revisit ideas, understand decisions, and move forward with more clarity. The more context your tools have, the more useful they become.
22
7
215
18,061
If your music is distracting you while dictating, we've got you covered.
21
4
98
17,548
Notetaker → Wispr Flow MCP → Claude → Linear MCP A seamless workflow starts with accurate notes 👇
17
3
120
12,337
We're hiring ML Scientists that want to help craft the future of HCI:
I'm looking for ML Scientists to work side by side with at our Wispr Advanced Interfaces Lab. This is the job I would have wanted more than any other coming out of Stanford. You'd be in the room for every modeling decision we make, and be crafting the future of HCI. We just previewed Canto, our first proprietary speech model, and it's the first of a rapid series. You'd own personalization, training speech models, and pushing LLMs further with fine-tuning and RL. The bar for this role is high: -PhD in machine learning or related field (neuroscience, EE, etc) -Strong publication track record at top conferences (ICML, NeurIPS, ICLR, ICASSP) -Creativity in R&D, excellence in engineering, and code velocity If you're this person, or know this person, drop a reply or tag them. jobs.ashbyhq.com/wispr-flow
4
22
7,397