Published On: November 1, 2023

Fairfield, CT – TVEyes, a global provider of audio and video intelligence tools for data-driven professionals for more than 20 years, today announced that it has implemented a new speech-to-text (STT) solution across its podcast dataset that directly transcribes spoken language into text, eliminating the requirement for intermediary processes or components.

“We have a long-standing commitment to continuously improving speech-to-text,” TVEyes Chief Commercial Officer Daren Benzi said. “By leveraging the unique expertise of TVEyes Language Technology Labs, the first-of-its kind endeavor dedicated to the expansion and advancement of speech-to-text technologies, we’re able to efficiently expand and bolster our STT models.  Today’s announcement further symbolizes our commitment to our customers and partners of continuous and progressive technology and product improvements.”

The result of the enhancements announced today include an improved transcription output using cutting-edge technology and leveraging neural networks to directly convert spoken language into text. For end customers, the STT enhancement offers high accuracy, real-time processing, and a streamlined workflow. The new STT solution is currently in use for podcast solutions and will be rolled out to broadcast solutions in the coming quarters.

To learn more about TVEyes and its commitment to speech-to-text innovations, please visit: