Compare Trint vs. Whisper

The easiest way to record, transcribe, and share your phone's audio right from your smartphone! Trint's mobile application lets you capture the important moments, wherever and whenever you want. Wired: "Amazing!" Google - "Rocket-fueling Innovation!" We know that work doesn't always take place in an office. So we created the mobile app to allow you to access Trint's AI transcription wherever you are. You can record live interviews and import files directly from your phone without any complicated equipment. All you need is the app! Record live conversations. Trint can import audio files from other apps. You can share transcripts and assign editing permissions in-app. Trint transcripts can be easily followed by an intuitive player. All files are saved to your device and to the cloud, so you don't have to worry about losing any. Download audio to your device. While you record, drop markers from your Apple Watch. You can capture in 28 languages right from your iPhone, including English, Spanish and Chinese Mandarin, Hindi, and many more.

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.