Hey HN! I’m Christian, daily lurker and some might remember our original launch post (https://news.ycombinator.com/item?id=42935355). Today we're launching Pinch for Mac, which we believe is a step-change improvement in real-time AI translation. Our vision is to make cross-lingual conversations feel as natural as regular conversations.
TL:DR During an online meeting, the app instantly transcribes and translates all audio you hear, and allows you to decide when you translate your voice and when you don't. It's invisible to others (like Granola), and works everywhere without any meeting bots. Try it at startpinch.com
Here's a live demo we recorded this morning, without cuts: https://youtu.be/ltM2p-SosLc
When we first launched Pinch, we shipped a video conferencing solution with a human-like AI interpreter that was an active participant in your call. Our users hold the spacebar down while speaking to the translator, and when they release the spacebar the translator speaks out to the entire room.
That design was intentional - it puts the task of context selection on the user and prevents people from interrupting each other awkwardly (only one person can press spacebar at a time). It also comes with heavy tradeoffs, namely:
* Latency - Up to 2x longer meeting lengths due to everyone hearing your full sentence and then the translation of your full sentence
* Friction with first-time users - Customers using Pinch for external communication often meet with new people each time, and we've learned of several that send out an instruction doc pre-meeting on how to join and use translation in the Pinch call. Bad signal for our UX.
* Restricting our customers to those who are meeting creators
Benefits of the desktop app:
1. It creates a virtual microphone that you can use in any meeting app
2. Instant transcription+translation means you can understand what's going on in real-time and interrupt where necessary
3. Simultaneous translation - after you start speaking, the others will hear your translated audio as fast as we can generate it, without interrupting your flow.
Over the last months our focus has been on developing a model and UX to support high translation accuracy while automating context selection - knowing exactly when it has enough words to start the translated sentence. We’ve rolled this out to the desktop app first.
We're incredibly excited to go public beta today, you can give it a try at www.startpinch.com
Cheers, - Christian
I encourage you to offer a “translation” option that involves simplification (e.g. Simple German) where the speech language X is translated in a simplified version of the language X. There’s value there.
Fun idea, are you thinking about a language learning use case?
That's also just a plain accesibility - levelling the situation where someone is less fluent in a given language. You could even translate from english to simple english!
Interesting. It's the oral version of "rewrite this paragraph to be understandable by someone with a 5th grade education".
Wild to think about.
There are some complicated words in German. When simplified have a translation. But in German it’s just, German. Streichholzschächtelchen. When one could just easily say Streichholzer.
It looks like whisper + google translate + google TTS. Typical "quality" for that stack, bad latency, no any privacy.
I'm developer of "Linguist", a browser extension for translation in browser, and I say you that nowadays it is possible to translate text locally in device. Linguist have embedded offline translator. The same with TTS and voice recognition.
All this features may run locally in-device, even in browser extension, but not in macOS application?
This product looks rather like a malware that will spy on users and then blackmail us or sell our conversations to email scammers for better targeting or anything.
Additionally it is interesting that Chinese and Korean languages is not supported. You just use cloud services, they are all support these languages, why you don't? Is it to fake something?
"12 hours translation per month" for $29. 12 hours it's about 6-12 meetings? Who is your audience then?
Let me just repost this tip:
If you add Deepgram listen API compatibility, you can do live transcription via either Deepgram (cloud) or OWhisper (local): https://news.ycombinator.com/item?id=44901853
Just need to polish the solution... I experienced some crashes with zoom.
I am the IDEAL user, willing to pay a lot if this works. Count on me feedbacks.
So far:
good: - initial config as good, easy and very simple to feel secure
bad: - high cpu usage - zoom asked me to restart mic - could not make sure if the software works... Google meet has not voice testing loop... Zoom has it, but it did not work for me.
Thanks for this feedback! We're rolling out an update soon that will allow you to hear your translated voice without joining a call. CPU usage is on the radar, hope to make some progress there soon as well.
also, voice matching is veryyy important
If you forget to pay your bill, you can still use it but your voice turns into that of a pathetic loser
Tried the beta - really cool! Would love to see more language options, awesome work!
Thanks! We're planning to add support for a lot more languages over the next two weeks.
Any equivalent Android softwares or SaaS to do this?
Just tried it, it works great! Any plans for offering it on mobile?
Our first focus is desktop, but we'd love to get a mobile app out (or let someone else build one with our API)
Does this work with less-than-perfect audio, for example, watching foreign TV with background music?
Yes, if you're watching TV on your computer the app should translate all the speech. We haven't done any source separation work (musical singing vs actual speech) so if there's music it may pick up some of the lyrics.
This is really cool, nice job!
Non-sandboxed macOS app, every single time! :D
I imagine virtual microphones are not covered by standard permissions under sandboxing.
Hey, this is very cool! I just tried to make something alike for Windows yesterday for talking in French (Bonjour le Québec). After a few hours fidgeting with Whisper, I ended up finding https://github.com/SakiRinn/LiveCaptions-Translator , but it does not have the virtual microphone feature. Do you plan to support Windows any time soon?
Yes, we're planning a Windows launch as well! If you need something today, we also have our own video conferencing platform with AI interpretation built in that works in-browser. It's at https://startpinch.com/meeting
[dead]