Pricing for Omny Studio's speech-to-text functionality:
Premium transcription: $0.24/min (USD)
Supports 29 languages (full list at end of this article), higher accuracy for publishing and premium solution. This is the default solution.
Basic transcription: $0.07/min (USD)
Supports 4 languages (English US, English AU, French CA, Spanish US), reduced accuracy for a higher volume and more cost-effective solution.
Once the feature has been activated, under each clip and recording there's a transcript tab where you can select your language.
An estimate of how much the transcript will cost and how long it will take is displayed in this window. Once you're happy, click Generate Transcript and you'll be emailed once it's completed.
You can edit the transcript as required and low confidence words will be highlighted in orange. You can also seek through your audio using the text editor by ticking "seek and play on word click"
Once you're happy, you can download the transcript as an SRT or Web VTT and if you make any changes that you want to revert, you can either undo or go back to the original transcription under the same tab.
If you have clean audio, the difference between premium and basic transcription is minimal.
This simple example may help when choosing which engine will work best for you.
"this is an example clip on on the studio and this is the end of that clip"
"This is an example clip on omni studio and this is the end of that clip."
Basic transcription is often very good with minor mistakes such as the one in the above example. Premium transcription is not perfect but it is more consistently accurate.
Please let Omny Studio support which engine you would prefer. Changing between engines can be done on request. Previously generated transcriptions can not be re-generated with a different engine.
Full list of languages: