Krisp Accent Conversion

Understand accented speech in real time

Productivity

Artificial Intelligence

Audio

This has been a long build. Accent Conversion is one of the most practical features we’ve shipped. Thanks for checking it out.

This is a really clever approach - solving it on the listener side instead of asking the speaker to change is such a smart product decision. We work with people from all over the world and the "smile and nod" moment is too real. Curious about one thing - does this work well in group calls with multiple accents at once, like a meeting with 5 people from different countries? Or does it work best when it's mainly one speaker at a time?

Congratulations on the launch! It’s truly amazing that it can achieve real-time accent conversion! I have a question, what’s the typical delay in seconds from when someone speaks to when the accent adjustment is processed? If the latency is high, would that affect my ability to respond in real time during meetings?

Useful, I recently traveled to India and had problems understanding people, having to ask them a couple of times to repeat what they just said and felt uncomfortable doing that. Can this be used for non-work related situations as well?

I’ve been looking for a solution like this, and I'm quite impressed by the demo showing such low latency in real-time audio processing.

As a developer myself, the seamless UX really stands out. Was it a big challenge to integrate the AI summary feature into the existing desktop app architecture? Looking forward to trying it out!

Hey @asti_pili,

After your PH launch I looked at Krisp’s positioning. right now the hero focuses on AI noise cancellation and transcription, but there’s a strong business case around reducing miscommunication costs & boosting team meeting productivity.

That outcome focus could materially improve signup and paid adoption for teams.

Want a short positioning + revenue hypothesis doc?

This is DOPE! Just like others, would love to see a Chrome extension. Congrats!

Thick accents are always a struggle for me to understand ao this is really helpful! Congratulations on the launch!

Really impressive that this runs fully on-device with near-zero latency - thats a huge win for privacy and usability on global calls, and the listener-side approach is smart because it removes friction without asking speakers to change anything. Quick question: how well does the accent conversion handle non-native speakers who code-switch between languages mid-sentence?

The on-device processing is what stands out to me. Curious to see how this evolves^^

My friend recommended Krisp to me since I just started working from home and noise cancellation is the only way to go to reduce that background noise anxiety. Do you have some kind of crazy discounts for paid ones like a $1 a month.?.. hehe @Krisp

This is HUGE! I have a terrible time understanding some of my teammates and I feel horrible always asking them to repeat themselves.

This is super cool! Curious how well it handles overlapping speakers / fast back-and-forth conversations?

I tested it and...whoa! I love it!

It's a pity I only get 60 minutes a day, as I'm already paying for the subscription I was expecting this to be included.

How do you do that by the way, is it locally executed? As there is almost no latency, it must be.

I work with contractors in four time zones. It's the mental tax of re-parsing every other sentence while trying to stay in the conversation. Does this run locally or does audio hit your servers? I'm prepping my own launch soon and real-time audio latency is something I think about a lot.