Really like the fact that it's easy to start doing something useful. I may end up using it for some screen scraping too. Puppeteer is powerful, but the scripts tends to be brittle.
the fact that it's open-source and nicely structured internally lets you "peel off" the topmost YAML layer and just use the underlying components to interact with the mobile device, using your JVM-compatible language of choice.
Awesome to hear! There's still tons we want to do on the Web side, so please let me know if there's anything you think should be added or improved there! Feel free to tag/DM me (@Leland) in our Slack community or email me leland@mobile.dev with questions/suggestions!
(Creator here), sure I just added something so you can play with the URL: https://firehose3d.theo.io/?speed=0.9 (but if you slow the movement down too much there will just be way too much content because it's real time)
The tech is really here. This summer, I was fascinated the accuracy by the spoken language auto-detection capabilities. It really works and it only needs 1-2 seconds to catch the nuiance of a specific language.
> Many fixes have been incorporated in the past two weeks.
Thanks for the efforts! Still many fixes to go, though: I used the version from two days ago, which had numerous issues. Also, 3PO isn't offline, so I won't be pursuing it.
No problem! Some fixes were on the server side. We had a server side issue a couple days ago for a few hours. You may have been affected by it, giving you those errors. They have been fixed too. Take care!
It works really well for me, but I wish it supported more languages for the input - i guess this is a limitation of the model you are using? Do you mind giving some info about the tech stack? I love how fast it is.
thanks for the kind words!! It is built on top of a fairly straightforward infrastructure. Client side is C#, .NET, MAUI. Server side is Firebase Cloud Functions/Firestore/Web Hosting + Azure.
Thanks - I was wondering more about the translation pipeline - i am assuming something like whisper and m2m100? How did you manage to get the latency so low? Other examples I have seen feel really sluggish in comparison.
So far all looks interesting. The only thing that I’m still wrapping my head around is the pricing/licensing for “indie”
If I may suggest, instead of 6 month audit and machine locked license, perhaps something like where license is needed IFF the app is launched. This will reduce friction for individuals and pre-funding startups. I believe Unity and Unreal use this kind of licensing.
For me for "Indie" pricing is not clear what it means "members with less than 30K USD related annual revenue" Does it mean less than 30k revenue from app using Skip? Or any revenue such developer has? If the latter then any freelancer or indie will not qualify if have monthly salaries >2500usd doing any IT stuff or app dev using different frameworks.
Yes, their pricing/licensing is not ideal at the moment, IMHO of course.
They need to build critical mass and hence initial tinkering should be as friction free as possible. Landscape is full of alternatives so people need to get started as quickly as possible.
They seem to have a valuable product, but this initial friction might reduce traction, again IMHO.
A speech-to-speech translation app, with automatic language identification. One touch interface to start/stop. No configurations required for everyday use cases.
That's the plan... :-) It can auto-detect 45 languages now, including Chinese, Japanese, Arabic and most European languages. (like in sci-fi movies, it allows two users to share a pair of airpods to talk to each other in different languages.)
This really is a landmark success. Their patient, Harrell, who suffers from ALS, can use their Brain-to-Speech interface daily reliably (<3% error rate) to talk to family.
That statement is an outright lie too. Not only are they operating at less than 1% of what the free plan offered, but the email doesn't tell them the honest truth: That the free plan is reaching sunset, and they want all API users to switch to a paid plan.
This isn't unreasonable, but they absolutely should provide more than 1 business day notice.
Of course it's generic and perhaps not a technically correct statement. And now? Why should they spend time on writing you nicer emails? What was your value to them? Zero? Or is that too optimistic actually?
Really like the fact that it's easy to start doing something useful. I may end up using it for some screen scraping too. Puppeteer is powerful, but the scripts tends to be brittle.
Keep up the good work!