YobiYoba
Pay-as-you-go speech-to-text service that transcribes audio and video files into time-coded, editable transcripts.
About
YobiYoba is a web-based transcription platform that converts audio and video recordings into accurate, time-coded text. It automatically detects the spoken language, labels speakers, and produces transcripts you can edit directly in the browser before exporting.
Supported export formats include PDF, DOC, RTF, CSV, SRT, and VTT, making it useful for media producers, researchers, journalists, and content creators. Custom word lists help improve accuracy for specialized vocabulary.
Pricing works on a pay-as-you-go basis starting at around 0.01 EUR per minute with no minimum fees and non-expiring credits. Volume discounts apply for larger batches. There is no free tier, so this is a contact-based or direct-purchase paid service.
Supported export formats include PDF, DOC, RTF, CSV, SRT, and VTT, making it useful for media producers, researchers, journalists, and content creators. Custom word lists help improve accuracy for specialized vocabulary.
Pricing works on a pay-as-you-go basis starting at around 0.01 EUR per minute with no minimum fees and non-expiring credits. Volume discounts apply for larger batches. There is no free tier, so this is a contact-based or direct-purchase paid service.