Revolutionary speech recognition:

Pioneering solutions for education and more – accurate, secure, and best in class for children’s voices!

Our speech recognition captures not only WHAT is said,
but also HOW it is said.

Number 1 worldwide for German children’s voices

Our speech recognition technology is specially optimized for children’s voices and sets new global standards in precision and accuracy.

Compared to other solutions available on the market, it offers the highest recognition accuracy for applications where spoken words need to be transcribed aloud – ideal for use in schools and educational programs.

RECOGNITION ACCURACY – STATUS NOVEMBER 2024

Digi Sapiens 91,6% 91,6%
Google 80,7% 80,7%
OpenAI Whisper 69,2% 69,2%
Microsoft Azure 68,1% 68,1%

Source: Own survey using transcribed reference data set from real-world data (noise exposure, accents, use of smart devices)

w

Robust against accents

Our speech recognition (ASR) works reliably even with reading errors and is robust against accents and dialects. In addition, it offers a unique pronunciation analysis based on phonological features.



Speech melody analysis

Our audio analysis evaluates prosodic characteristics such as speech melody or speed, providing additional important parameters for determining reading competence.



Precise analysis through targeted comparison

Through a sophisticated comparison of the target text and what has been read, we identify various reading errors and their exact position in the text. This analysis not only allows a precise assessment of reading skills, but also reveals the individual weaknesses of the reader.