Compare Rev vs. Whisper

Rev offers premium on-demand, manual, and automated transcription, closed captioning, and foreign subtitling services. Rev has 170,000+ clients, ranging from freelance journalists to global corporations. Rev processes more audio/video than any other provider, and can scale to meet any customer's requirements. Pricing is straightforward, starting at $0.25 per audio/video min for automated speech-to text services and $1.25/min manual with 99% accuracy. Rev.ai is a speech recognition engine available to companies who request it.

We have developed and are releasing an open-source neural network named Whisper, which achieves levels of accuracy and resilience in English speech recognition that are comparable to human performance. This automatic speech recognition (ASR) system is trained on an extensive dataset comprising 680,000 hours of multilingual and multitask supervised information gathered from online sources. Our research demonstrates that leveraging such a comprehensive and varied dataset significantly enhances the system's capability to handle different accents, ambient noise, and specialized terminology. Additionally, Whisper facilitates transcription across various languages and provides translation into English from those languages. We are making available both the models and the inference code to support the development of practical applications and to encourage further exploration in the field of robust speech processing. The architecture of Whisper follows a straightforward end-to-end design, utilizing an encoder-decoder Transformer framework. The process begins with dividing the input audio into 30-second segments, which are then transformed into log-Mel spectrograms before being input into the encoder. By making this technology accessible, we aim to foster innovation in speech recognition technologies.