How it works
You describe. We transcribe.
Upload your audio
We currently provide transcription services in English (Chinese in early 2019). Support audio files in .mp3 or .wav format.
Describe the context
Tell us the context of your file, so we can understand all of the acronyms and jargons that were mentioned in the audio.
We process your audio by first using artificial intelligence, then either yourself or one of our human transcribers can make sure the transcript is accurate.
Commonly asked tidbits.
How long does it take to get my transcriptions?
Depends on the size of the file :) Usually it takes less than the time length of the audio file to generate the draft, which is ready for you to review.
If you would like our transcribers to proofread it, a few additional hours would be required.
What is your technology?
We use deep learning - a class of machine learning - to build our artificial intelligence model. This is the same technique adopted by Google, Amazon, IBM and Baidu to build their speech recognition related products.
Do you offer on premise solutions instead cloud?
We are working on this right now but currently we only offer our solutions via cloud.