Almagu has been one of the leading text-to-speech (TTS) companies in Israel since 2011. Our products are sold to major companies across a variety of sectors—from telecommunication, education to healthcare and public sector. Our synthetic voice technology is used by most colleges and universities across the country, helping thousands of students to communicate better.
In the health sector, Ezer Mitzion, one of the leading Israeli health support organisations, has implemented our digital voices in communication computers used to aid patients in need of Augmentative and Alternative Communication (AAC) solutions. Since 2015 we have also been part of the Israeli government programme to fund communication means to those who need them.
It was in 2015 when we received our first request for a personalised text-to-speech (TTS) voice generator for an ALS patient. Little did we know that this request would set us on a new path.
The patient was already in the advanced stages of the illness and couldn’t talk very well. He had done some recordings in the past but their quality was not good enough for the technology at the time.
We were desperate to help him and other ALS patients who wanted to communicate with their loved ones in their own unique voice. That’s when we set off on a long mission to create an intuitive and affordable system of personalised voice creation.
The breakthrough for us came in 2018 when we started to experiment with Deep Neural Networks (DNNs) in the synthesis technology.
Why? DNNs offers several significant advantages over the traditional synthesis technology which most voice banking solutions currently use.
Fast learning – DNNs’ fast learning capabilities significantly reduce the number of sentences a person needs to record in order to create a personalised digital voice.
Background noise filtration – Additionally, the networks allow better background noise filtration because of their lower sensitivity to the recording environment.
Reduction of inconsistencies – This means that the quality of the recordings is significantly better than with previous voice banking technologies, and this means that people with slightly slurred speech have the opportunity to use their voice to create a digital voice.
Combining efficient use of DNNs with Almagu’s previous experience eventually led to creating our product — The Voice Keeper.
In March 2019 we launched The Voice Keeper in Israel. Our system is fully automatic, performs quickly, and is very easy to use. We take personal care to guide users through the recording process, alerting them if something goes wrong and advising them on how to achieve better results.
Months of intensive testing has allowed us to significantly improve The Voice Keeper and uncover its real magic.
Leveraging the lessons learned in the Israeli market, we improved our voice banking system to now empower patients in the English-speaking world.
The Voice Keeper technology is faster than other voice banking solutions currently in the market – It only takes 3 minutes to get started! The more you record the better the technology will become in capturing your personal voice, accent and the way you speak.
The technology works around your schedule – You can choose to record 30 sentences in a day or 100 sentences every second day. It’s up to you and every time you reach 100 sentences, the technology will send you an updated version of your digital voice.
Improve your voice gradually – This means that on average you can spend 10 minutes a day recording for 4-5 days in order to create a personalised digital voice.
Industry healthcare professionals advise ALS and MND patients to preserve and create a digital voice as early as possible while it’s still strong. To facilitate this we decided to make voice creation free, and only charge when people are ready to use their voice on a communication device. We launched a keeping service which allows users to keep their voice safe in our database for a marginal fee until they really need it.
At Almagu, we make creating personalised synthetic voices easy and intuitive.
Our mission is to enable people who are at risk of losing their voice to preserve it with minimal effort!
Working together with patients, their families, doctors, speech and language therapists, and medical institutions we strive to increase the impact of our technology.
We are excited to enable ALS patients to preserve a key part of their identity – their voice.
Interested to explore how you can use TheVoiceKeeper’s technology in your work or institution? We’d love to discuss this with you.
A speech technology veteran. With 20 years of experience in leading development teams he is in expert in delivering high-quality solutions, whether it comes to apps or server applications.
Ariel makes sure your voice sounds best, taming all the algorithms and data along the way. He’s celebrating his 18th birthday soon, and we hope to stop the time, so he won’t have to go to the army.
A master of Windows technologies and SQL, Andrey built most of our services from scratch, with his bare hands (not really).
Eli is bringing in more than 40 years of experience in selling speech products and high-tech software, services to Israel’s largest organisations.
Yael is designing all our products since 2013