Show HN: Oasis AI – Craft Emails, Essays and Notes, Just by Talking
apps.apple.comI’m Yousif, founder/CTO of OASIS AI, a new iOS app to elevate your communication skills.
https://apps.apple.com/us/app/oasis-ai/id1668222944
OASIS AI transforms natural speech into polished writing—college essays, business emails, social media posts, journals, and more. Everything is instant, automatic and efficient. and efficiency. It’s very simple.
Let’s face it: humans communicate constantly, but we suck at it.
We want to use LLMs to go beyond Grammarly's error correction and Google Translate's word-for-word translation. Instead, OASIS refines your thoughts and intentions, choosing the perfect words to express your ideas in any format or language. The app gives you a first draft, a starting place, and then you’re in control from there.
OASIS started off as English–to-English, and we are now in the process of rolling out language translation and speech transcription for over 30 languages, including Chinese, Japanese, Spanish, and Arabic. As a preview, the app enables English speakers to craft WeChat posts that mimic the casual writing of a native Mandarin Chinese speaker.
What do you think? What features should we add? How can we be better?
https://theoasis.com/ Been using this for the past few weeks. I find the ability to speak in a free-form way quite liberating. I feel like it opens up a new, more creative mode of thinking, different to internal monologue or writing. The LLM based summarisation leaves me with the core arguments + conclusions from the lengthy monologue & enables me to repeat myself or pause for lengthy periods to think. thanks for being a beta user! Where do you find yourself using Oasis most -- at your desk, on the go, etc? What subjects to you mainly use it for? What can we do to make it better and more useful for you? I've been watching this application grow since its early stages, and not only is it a useful, practical, and an "ahead of its time" tool, but the team putting it together is top notch. Motivated to make a difference,
Oasis is the next big thing to watch. thank you for your support! There is no explanation for what "a credit" gets you? i.e. how are people supposed to know, when they are prompted to pay after the first 10 minute test, how credits are to be interpreted? I.e. is a credit 1 minute? is it 10 minutes? This should be described on your app home page, or at the very least in your terms of service. I cannot find it anywhere. Also, the content user license is unsettling - giving you irrevocable rights to the user's content throughout the world into perpetuity (including the right to transfer). I would recommend that if your audience is entrepreneurs / experts / thought leaders / content creators, that you balance this language with some thought for the user's desire to protect their IP. I've been beta testing the app and my favorite use for it so far is using it to capture my thoughts about the day when driving in to work. I really appreciate having "better than OS quality" transcription. (Disclaimer: I invested in the company.) I wish I could record longer than 10min or if there were at least a chime to indicate the recording is ending / has ended. I also hope to get more of a TODO list I could then further organize. But what's there is pretty neat and already useful to me. Hey! We're thinking about adding a CarPlay app where you can just tap record on the screen (and tell siri to start a recording). Would that be helpful? Also, >10m recording length coming soon! It would be...except Apple does not permit CarPlay entitlements to request recording entitlements except for narrating a navigation destination. So you may find this is not possible. You'll note Apple's own Voice Memos app isn't available on CarPlay! Love the app and use it as a thought log all the time! It would be great if I didn't have to select the output type upfront but rather just free-flow dictate. I don't always know if something will turn into a blog post or small tweet at the time I am dictating. If you could summarize the content into a few words (similar to how ChatGPT names its chat thread), and I could generate a specific output type from that list in the history, that would be a game changer for me! You can already do that! Just deselect all the outputs on the main view (it will just give you a transcript in the history). Then in the history section, after you select the recording, you can click "Add Output" (or Add Response depending on the version of the app you have). we both wrote the same thing at the same time lol You can do this now. 1. on homescreen, tap "Select Outputs"
2. de-select all the prompts: tap "select all" in the lower right twice and none of the prompts will be selected
3. record a new voice note
4. in the output view, tap "Add Outputs" LMK if this works for you. Didn't realize I could unselect all, thank you so much!! cool idea! Been using it since alpha stage. Love the way I can ramble and it turns it into coherent paragraphs that I can edit for my recap of meetings or to prepare drafts of emails :) glad you're finding it useful! How can we make it even better for you? This is very neat and I’m keen to see if I can make use of it! One note, I downloaded and dove right in with some nonsense and used up 17 of my trial tokens, unknowingly. It definitely made me understand how the app works but it was a surprise, and an expensive way to learn! Not trying to get them back but just a thought that there may be a friendlier way to introduce folks to the experience. Thanks for the feedback. The next update of the app (tomorrow) will have many less outputs selected by default, thus less credits used. We definitely need an onboarding as well. Any suggestions on how we can introduce users to the experience? I’m not sure about onboarding but to my eye the general UX kind of misses the mark on what’s valuable about this app. I see the app as basically “voice recorder plus” and in that regard it’s incredibly powerful. As you have the UX now, the app is more like “AI content creator that can only take voice input” which is less compelling and results in the initial flow you have now. I think a more straightforward “record than choose output” makes a lot of sense. I could see how “choose then record” would be efficient if I always knew I wanted to create a blog post, for instance, but absent that it’s overall off putting to have to think ahead of time what you want your output to be. If the initial (and usual) experience is “record something then we’ll ask what you want to create” I think it will unfold for new users much more clearly. Wow, super neat. This is going to be installed in every available ios/android device Yes! Love the app, not sure why wechat shows up as the first post type for me. The summary one would probably make the most sense as it allows me to know that I've been understood in the most concise form. We don't have a sort order on that list right now, but it will be there within a couple days! We will also sort by your most used outputs. Just tried it. I spoke and it turned what I said into a letter, a TikTok script, a song, etc. I can see how it'd be helpful for times when I know what I want to say but not how to say it. Just ramble and it turns it into polished writing. Thanks for trying it! Are there any outputs that you found to be particularly useful (or not useful)? Would be nice to confirm the transcription before it submits, or a way to start the recording over. My accent trips it up Thats a great suggestion. We are changing the speech-to-text model we use later this week, so it should produce much better results for you.
We will also be adding a feature where you can edit the transcript before submitting. Would that be helpful? Are you gonna use whisper? Could you support other languages? I prefer to talk in my native tongue but I am totally fine with the transcription being in English. I found whisper to be excellent at this Yes we are adding support for multi-language on the input and output sides. ASR will be switched to whisper later this week! Yes, that would be great! Keep up the great work, you have something good going here Very cool! Been wanting something like this for a while! What's the Android support looking like? :) TBD, but we may have something within a couple weeks. We're also working on a webapp. Oasis is a game changer. Forget prompts, planning, and creating 10 versions of something. Just download, turn it on, and talk. The first AI app I've used that effortly fits right in with how I work and think. Total game changer. Hi. I basically bought an Apple Watch for one app, Just Press Record. I'd love to see that kind of functionality added to your app, so I can always record my random thoughts, and it ends up summarized on my computer. YES!!! This is what I want most too! We will be adding this soon. Great! I look forward to it. The key for me is that it's a widget on the watch face. Glance at watch and with one click and I'm recording. If I have to fumble around with my phone or whatever to find and open an app, click a button, etc, I'll likely have forgotten whatever brilliant idea popped into my head before I get the recording started. We’ll make it happen! I'm Matt, Yousif is my co-founder and best friend. I'm extremely excited about what we're building at OASIS. Both of us are will be here to answer any questions, comments, etc. One of the coolest applications of gpt! Who doesn’t want their verbal brain dump to sound sophisticated? Looking forward to checking this out. interesting way to braindump. what models is it using behind the scenes? we're currently using gpt-3.5 and gpt-4 for the LLMs. We'll be adding support for more models under the hood in the future depending on the prompt / use cases. We’re experimenting and trying to do everything with the cheapest, smallest models we can, because ultimately we want to do it all on device This seems really cool, can't wait for an android version! might be something coming there soon ;) ples also send for android Dope