facebook-pixel

New record on accuracy.

Record domains speech-to-text accuracy

Once again, Vatis Tech goes beyond global giants by reaching a record accuracy of up to 95% in challenging areas for speech-to-text technologies, such as medical, legal or call center.

blog-press-release-18-10-2022.png

Over 2.3 million notes have been transcribed by using this Romanian technology so far.

The voice recognition technology based on artificial intelligence developed by the Romanian startup Vatis Tech for Romanian is reaching new milestones. The company announces the launch of new transcription models, designed for specific termed areas, such as medical or legal, but also for call centers, a huge transcription needs economic field.

Focus on these specific areas influences massively the efficiency and overall costs associated with the transcription activity or the operational business processes digitalized by implementing Vatis Tech solution for automatic transcription. For example, in the legal field, clerks no longer need to manually transcribe court sessions, doctors simply need to prescribe, and call centers can analyze large volumes of recorded calls.
Adrian Ispas, founder and CEO of Vatis Tech.

With the launch of the new speech-to-text models, Vatis also offers the possibility to install the technology on-premise, on the company's servers, alongside the cloud platform.

Following the demand from major customers and very large organizations, we decided to launch this on-premise version. Technology’s performance is exactly the same, regardless of whether the cloud version is used or the one installed on the client's server.
Adrian Ispas, founder and CEO of Vatis Tech.

Vatis Tech is well known for its high level of accuracy when compared to the big tech giants’ technologies. The new update released in October 2022 comes with a significant accuracy increase in the 3 areas mentioned above. Vatis Tech’s accuracy ratio in Romanian is 94.41% in the medical field, while Google or Microsoft gets 62.61% and 76.45%. In the legal area, Vatis Tech hits a 90.65% accuracy ratio, while Google and Microsoft get between 55.47% and 81.13%. On phone call audio recordings, Vatis Tech goes up to 95.00% accuracy, while Google and Microsoft get between 70.43% and 83.89%.

Recently, Vatis Tech broke the record of 2.3 million transcribed notes. Every month, around 400,000 notes and over 125,000 files are processed through this Romanian-born technology, and the numbers are constantly growing. It takes less than 10 minutes to transcribe an hour of audio or video content.

Vatis Tech is a company founded by Adrian Ispas, Alexandru Topală, and Emanuel Nazare, three experts in software development, in 2020. In September 2021, the company raised a 200,000 euro pre-seed financing round, from several investors (Early Game Ventures, Sparking Capital, and Mălin Ștefănescu) and it’s currently preparing for a new round.

Companies such as mediaTrust, Unicredit, Agerpress, Radio România and Gândul are already using Vatis Tech technology.

Vatis offers us a high standard, fast, efficient quality product. They are extremely quick when it comes to communication, which is one of our core needs. We can rely on them to provide highly accurate transcriptions of large volumes of linguistic data. Moreover, it is a pleasure to work with them.
Bogdan Apostol, CEO of mediaTrust

In order to use Vatis Tech technology, a user simply needs to create an online account at https://vatis.tech/ and upload the audio or video files that have to be transcribed. The free trial period includes 10 hours of audio or video content. Afterward, the transcription service can be purchased on a subscription basis from 3 euros/hour of content or 0.7 euros/hour for huge volumes.

In order to reach international expansion, Vatis Tech is seeking its second round of funding this fall.

Start building with Speech-To-Text today

1

Sign up for free

Get a free API token, and integrate into your code in seconds. No credit card required.
Start now
2

Start transcribing

Automatically transcribe audio and video files with high accuracy. Vatis Tech Speech-to-Text API is powered by advanced AI research.
Read our API docs
3

Understand your data

Automatically extract key insights and unlock the full potential of your data using our features.
View all features