In addition to live voice capture, Speech to Knowledge (STK) supports importing existing audio recordings. Whether you’ve recorded a workshop via Zoom, saved a training call, or downloaded a podcast—STK lets you transform it into actionable, AI-powered knowledge.
This feature is ideal for turning past recordings into searchable, structured knowledge.
Step-by-Step: Uploading a File #
1. Open the STK Module #
From the left sidebar, click “Speech to Knowledge”.
2. Click the Import Button #
In the top-right corner of the STK dashboard, you’ll see two options:
- 🎙️ Record
- ⬇️ Import → Click this one.
Step-by-Step: Uploading a File #
1. Open the STK Module #
From the left sidebar, click “Speech to Knowledge”.
2. Click the Import Button #
In the top-right corner of the STK dashboard, you’ll see two options:
- 🎙️ Record
- ⬇️ Import → Click this one.
3. Choose a File to Upload #
You’ll see a prompt to upload your pre-recorded audio. Supported file types include:
- .mp3, .wav, .m4a, .aac, .flac
- (Video file support coming soon)
Once selected, your file will begin uploading.
4. Wait for Processing #
After uploading:
- A “Processing your record” card will appear in your dashboard.
- STK will automatically run speaker diarization (i.e., detect who said what).
- You’ll receive a notification once it’s complete.
Tip:
You can delete a file while it's processing if you uploaded the wrong version.
5. When Processing is Complete #
Once diarization finishes:
- The transcript will appear in your dashboard.
- You’ll see a summary preview along with a toggle: “Add to Ex.Brain”
- Click the card to open the full STK session view.
Note:
Notifications for processing completion appear both in the notification center and as a red dot on the sidebar.
Next Steps
Once your imported file is processed, you can:
- Review the speaker-separated transcript
- Edit speaker names and details
- Export as summaries, SOPs, training materials, etc.
- Add to Ex.Brain or generate shareable documents