AUTOMATED TRANSCRIPTION
Automated Transcription
Transana now offers two options for automated transcription. Both options are server-based, so you may need to seek approval from your IRB or other ethical oversight board before using one of these services.
Transana integrates speech recognition technology from Speechmatics and from Deepgram.
The video below demonstrates automated transcription using Speechmatics. The process is essentially the same if you use Deepgram. Speechmatics is demonstrated only because it was the first service Transana implemented. Below the video, you can find details for each tool.
Automated Transcription – Overview
When creating a new Transcript or editing Transcript Properties, you have the option of selecting an Automated Transcription Method on the Transcript Properties form. (Please note that if you have a transcript in this item, it will be replaced by the automated transcript.)
At this time, you can select either Speechmatics Server or Deepgram Server.
When you have selected an Automated Transcription Method and pressed OK, Transana will run the Automated Transcription tool. This tool guides you through the process of audio extraction and submission of this audio data to the selected Automated Transcription service.
Both of the services that Transana currently supports provide time information with their data, so Transana includes time codes at the start of every sentence. They also includes estimates of transcription accuracy with their data. Transana color-codes these results, marking parts of the transcription with less than 90% confidence.
Please note that automated transcripts still require manual review and correction. Automated Transcription speeds the process of transcription in many instances, but the results can be uneven at times.
Speechmatics Server
If you select “Speechmatics Server” from the list of options, your request for automated transcription will be sent to and processed by Speechmatics.com. You must have an account with Speechmatics to use this functionality. (At this time, accounts include up to 4 hours per month for free.)
Select the language spoken in the media file. If you select English or Mandarin, you can select regional versions using the Transcription Language Locale setting.
Select the level of accuracy you desire, recognizing that Enhanced transcription is slower and more expensive than Standard accuracy.
Enter your Speechmatics API Key, which you can get from the Account section of the Speechmatics web site. This API key serves as your account name and password for Speechmatics.
Deepgram Server
If you select Deepgram Server from the list of options, your request for automated transcription will be sent to and processed on the Deepgram server. You must have an account with Deepgram to use this functionality. (At this time, Deepgram offers a $200 credit to help you get started.)
Select the level of accuracy you desire in your Transcript, which Deepgram calls the Transcription Tier.
Select the language spoken in the media being transcribed. If the language you need is not shown, try a different Transcription Tier. Note that some languages have multiple options to reflect regional differences.
Enter your Deepgram API Key, which you can get from the Account section of the Deepgram web site. This API key serves as your account name and password for Deepgram.
Important Note:
Using this function requires sending audio from your media file to an outside server. Please make sure you have IRB authorization for this process before using this feature of Transana. Please see the website for the automated transcription service you choose for information about their data handling and privacy policies.