Already have the recording? Upload an existing audio file or transcript into SageOx, from the web app or your terminal. Audio gets transcribed; a transcript skips straight to insight extraction.
When to use this
This is the path for content you already captured somewhere else. The other capture mechanisms cover live and video sources.
| You have | Use this | Not this |
|---|---|---|
| An MP3 exported from Zoom or a voice memo | Audio + transcript upload | — |
| A VTT or SRT from Otter.ai, Zoom, or Meet | Audio + transcript upload (skips transcription) | — |
| A discussion happening right now | web app recorder | this page |
| A screen recording or video walkthrough | Video import | this page |
A pasted or uploaded transcript skips transcription but still runs through speaker handling and insight extraction.
Supported formats
| Type | Formats |
|---|---|
| Audio | MP3, WAV, M4A, OGG, FLAC, AAC |
| Transcript | VTT, SRT, TXT, MD (skip transcription step) |
| Max size | 5 GB per audio file |
| Max transcript size | 256 KB in the web app |
Uploading a transcript skips transcription entirely. If you already have an accurate transcript, upload it instead of the audio; extraction starts immediately and you skip the transcription wait.
Upload from the web app
The fastest path for a single file:
- Go to your team's Media section
- Click Upload
- Drag and drop an audio file or transcript, or browse for it
- Add a title and tag participants
- Confirm to start processing
Processing starts automatically. You'll see progress in the pipeline view, and you can assign speakers to team members once transcription finishes.
Upload from the CLI
Import directly from your terminal without leaving your editor:
ox import accepts the same audio and transcript formats as the web app. See Import via CLI for all flags and options.
Upload many recordings at once
On a Mac, use SageOx Desktop. It uploads in the background while you keep working.
- Drag: select recordings or transcripts in Finder and drop them on SageOx in the Dock.
- Pick: choose Add a recording… in the menu bar and select them all.
SageOx Desktop doesn't take a folder: open it and select the files inside.
From the terminal, for scripts and AI tools
ox import takes one file per run, so loop over the files. Change *.m4a to match yours, such as *.mp3 or *.wav.
- Safe to re-run: ox skips any file it already imported, matched by content hash. Run the loop again to retry a file that failed. Add
--forceto import a file again anyway. - Pick the team: outside a SageOx project, and with more than one team, add
--team <team>. - Web uploads aren't matched: files you uploaded in the web app import again. Move them out of the folder first.
Or hand the job to your AI tool, such as Claude Code or Codex:
How processing works
Audio uploads run the full pipeline. Transcript uploads enter at the insight-extraction step, since the text already exists. Either way, the extracted decisions and action items commit to your Team Context for your AI coworkers to read.
What's next
- web app recorder: record a live discussion in your browser
- Video import: import Loom, Figma, and Cap recordings
- Discussions: what discussions capture and how they're stored
- Distillation: how recordings become team memory