We run servers in the US and EU. If data privacy is key, we have on premise solutions. Please contact us.
This information is detailed in our privacy statement.
If there are words in the text that are not in the audio provided, then the alignment process can take longer than expected. This can be improved by removing these words, or surrounding them with the
Any words in the text that are not in the audio provided should be removed or surrounded by
<> marks. This will improve the ability for the alignment task to operate accurately.
Yes, we do! The text for alignment must be uploaded in UTF-8 format right now.
Yes, Speechmatics provide this feature, and there is no requirement for multichannel recording.
The better quality the audio the better the transcription will be. Things that impact the accuracy of the transcription are:
- Clarity of the speech
- Background noise
- Cross talk or multiple speakers at the same time
We try and build the best speech technology wherever possible but know that we cannot be the best at every use case. Best to give us a try here and see if our system works for your use case.
There is no minimum file size. For non-contracted customers the minimum charge is for 1 minute (even if the file is shorter than that) and then charge for every subsequent 10 seconds. The maximum file size is only limited by the time taken to upload the file. The file upload will time out if the file takes any longer than 2 hour to upload.