Speechly is the fast, accurate, and simple Voice Interface API. Our proprietary technology lets developers with no speech recognition or NLU experience easily add multi-modal voice UI functionalities into any digital application with just a few lines of code.
@ottomatias_speechly Thanks!
Yes, you can very easily add voice capabilities to your search functionalities by adding a couple of snippets of code, here's an example: https://codepen.io/speechly/pen/...
The Speechly API provides real-time NLU capabilities in addition to speech-to-text so it allows you to build voice enabled experiences that understand the meaning of the user and react to that _while_ they are still speaking. This results in a natural great user experience. Check out the demos at our website: https://www.speechly.com/demos
Report
I've had a great experience using Speechly to build prototypes of voice web apps here at the BBC. As a designer they've provided me with brilliant support to help me integrate Speechly into my code. Highly recommended.
@antovtok Thank you Tom, appreciate your feedback. We believe that every website and application can benefit from adding voice features to remove user friction related to e.g. searching, inputting or other tedious tasks the users might face as part of the overall user experience :) But voice is not a replacement for a GUI, but rather a complement to make it faster and easier.
Report
Speechly is a great product, built by a talented team of people!
Using your voice to fill out forms handsfree is a game changer. I especially hate filling out forms on mobile devices. Keyboards take up half the screen, and the formatting of the other half with the field often gets messed up.
But with voice you can see the full screen, and your hands are free to hold the device or do something else.
Good luck Otto, Collin and the rest of the team!
Hey Product Hunters!
I'm Otto, CEO and one of the co-founders of Speechly. Thank you Michael for hunting our product.
When we started building Speechly back in 2016, we had a vision: Do for voice what Apple did for touch by building voice UIs that actually work. We've been heads down working on the product in the years since. Having worked on Siri and Alexa, our founding team knew that voice had far more potential than living inside of a speaker and telling jokes to kids.
We spend so much of our day engaging with websites and apps. When it takes longer to get something done or the experience is frustrating, it can stack up over time and steal time away from doing things we love. The true power is unlocked when someone can use their voice to make something happen, any time, anywhere. Where we can add efficiency and decrease frustration, let people speak and feel heard, that's important to us.
To realise this dream, we have spent thousands of hours building our technology stack that makes it possible for our API to process and generate reactions to speech in real time, as people talk. We focused on building the core technology to be fast to respond, super accurate and simple to use. It was also really important to us that we make this something that could be used horizontally, across all major browsers, mobile applications, physical products and in the metaverse by every product and development team out there.
For the end user, Speechly's technology allows for real-time visual responses in the UI to what they're saying as they say it. They can speak naturally and be understood with 95% accuracy, and it makes for a really fast and positive user experience.
For developers, Speechly's API makes it easy to add high accuracy voice features as UI elements without completely rethinking the tech stack or user experience, or spending hours trying to train machine learning models. It's a simple, fast implementation and it's really easy to manage long term, too. So faster builds, faster deployments and happier & more productive users.
I mentioned we've been building since 2016, focused almost exclusively on the core AI and Deep Learning technology. We've now got the core technology built and patented, our dashboard is looking ✨ and we are so proud and excited to share Speechly with you! You can start building for free - we can't wait to see what you create 🤓
We would love to hear your feedback - what do you think, how can we improve, what are you imagining building with Speechly. All feedback is highly appreciated 🙏
Happy Hacking!
Best regards,
Otto
Report
Speechly is a strong entry in the online automatic speech recognition with natural language processing. If you are looking for a way to add ASR to your web project, no matter your platform targets, Speechly is the fastest, most robust way to get up and running quickly. I literally went from reading their docs to integration inside of a day. Speech recognition is fast and accurate across a range of platforms and mic profiles. Speechly's built in correction code and out of the box web components make everything go faster. With a focus on developer friendliness, correctness, and speed the Speechly platform is a best in class choice if you are looking for an ASR solution for your web application.
@ryanhollander Thank you for the review and kind words! This means a lot to us especially coming from such an experienced person in this field as yourself! 🙏
Report
@superotto Aw shucks. You're most welcome, it's well deserved!
Speechly Reactive Voice UI API
Speechly Reactive Voice UI API
Speechly Reactive Voice UI API
Speechly Reactive Voice UI API
Speechly Reactive Voice UI API
Speechly Reactive Voice UI API
Speechly Reactive Voice UI API