💡We recommend the following file formats:
Audio: ".m4a" format
Video: ".mp4" format
※ If upload takes a long time with formats like ".mp3" or ".wav", please convert audio to ".m4a" and video to ".mp4" and try uploading again.
💡 List of Supported File Extensions for Upload
◆ Audio Files
mp3, m4a, wav, aif, aiff, flac, alac, aac, ogg, wma
◆ Video Files
avi, mov, wmv, flv, mpg, mpeg, mp4, mkv, webm, asf, ogm, qt, m2ts, mts, ts
1. Click "Upload"
2. Select "Choose File" or drag & drop to upload the file you want to transcribe.
3. Before transcription, select the following and click "Transcribe with this content":
Upload team
note save destination folderMain language
Used for transcription and AI summarizationSub language
Used for transcribing multiple languages Up to four languages maximum
4. After upload, voice recognition analysis begins.
An upload completion notification will appear in the bottom right of the screen, and a note will be created.
The note will display "Voice analysis in progress" with an orange gauge showing the progress.
Analysis time varies depending on the amount of text to analyze (1 hour of audio: approximately 5 minutes)
※ If analysis doesn't complete after some time, try reloading the page.
5. When the "In progress of voice analysis" display disappears, your note (transcription/summary) is complete.
Click on the note or click the file icon displayed in the "Upload completed" notification screen. The analyzed note will open.
Use AI Chat to organize meeting minutes, edit transcription and set speakers.
If you have enabled the summary feature setting (editable by administrators only), you can edit or refine the summary.
