Omny Studio now has speech-to-text functionality as part of their platform, enabling radio stations and podcasters to transcribe their audio content. 


“The automated transcription of audio is an important enabler to growing its discoverability,” says Chris Johnson, Head of Digital Product & Innovation at Southern Cross Austereo, “Omny’s latest transcription capability will not only assist with audio production, but will help optimise audio for search engines, social media and AI platforms.”

Leveraging Amazon Transcribe and the Speechmatics’ advanced automatic speech recognition (ASR) engines, publishers using Omny Studio can now transcribe their audio with 29 different language options. The languages include American, British and Australian English as well as Spanish, Danish and French, amongst others. The transcription can then be edited in Omny Studio and exported into industry standard subtitle formats WebVTT and SRT. 

Sharon Taylor, CEO of Omny Studio says, “In the first release of this feature, on top of repurposing interviews and breaking news for written articles, radio producers will be able to search through our on-air archive for specific topics or keywords.”

In an upcoming upgrade scheduled for later this year, transcriptions will be incorporated into Omny’s embed players and stand-alone web player so listeners can quickly search and seek to specific moments or keywords. The next version of Omny Studio’s audiogram tools will also integrate word-by-word subtitles to further enhance sharing audio on social media.

The ability to transcribe audio is now live and available today, for all Omny Studio clients around the globe.