Accurx Scribe now includes an audio upload option in Accurx Desktop, Web and Mobile, so you can upload a pre-recorded consultation, dictation or meeting and use it to generate a Scribe output.
Audio upload is especially helpful if you are working in an area with low or unstable network connectivity, or if using Scribe live is not practical at the time.
💿 When to use audio upload
Audio upload can be useful when you are uploading a recording after a consultation, working in low-connectivity areas, or using dictation that you want Scribe to process later. It is available in Accurx Desktop, Accurx Web and the Accurx app (Mobile), so you can use it in the way that fits your workflow.
Before you start, make sure your browser or app is up to date and that your file is one of the supported audio types 👇
ogg
wav
mp3
Please also ensure your file size is not larger than the maximum limit of 100MB.
⏺️ How to upload audio in Scribe
Accurx Web and Accurx Desktop
Open Scribe and select the audio upload icon (outlined in the screenshot below).
Select your audio file from your device.
Scribe will process the upload and generate an output for your review.
Accurx App (Mobile)
Open Scribe and select the audio upload icon (outlined in the screenshot below).
Select your audio file from your phone or device.
Scribe will process the upload and generate an output for your review.
It is essential that the clinician reviews all of their Accurx Scribe outputs before they are added to the medical record or shared with patients and other services.
⚠️ Reporting issues: We are constantly improving Scribe and value your feedback. If you notice any hallucinations/omissions, please let our support team know via the live chat button (bottom right of your Scribe window). Reporting these helps our team review the output and continue improving the tool's accuracy.
Hallucinations: Any false or misleading information that was added.
Omissions: Any relevant clinical information that was missed.
How audio upload works
Audio upload is processed in a way that supports reliable handling of the recording during transcription.
The audio is processed temporarily to create the transcript and note output, rather than being kept as a stored, uploaded file.
💡 Tips for best results
You will usually get the best results from a clear recording with minimal background noise.
Check your connection before uploading, especially for larger files. It may take a little longer to process a long recording (>30 minutes).
🛠️ Troubleshooting
If an upload fails, the most common reasons are:
An unsupported file type
A file that is too large
An unstable connection
An out-of-date browser or app.
If the transcript quality is lower than expected, this is often due to the quality of the source recording, background noise, or how clearly the speaker was captured.
If you have any further questions or feedback, please get in touch with our support team using the message bubble in the bottom right-hand corner of this page 👉