Store transcripts and documents where you can search them
Transcripts, notes, exports and reports are only useful if you can find them later. Send them to Stow (usestow.com) as files or plain text, tag them with what matters to you, and search by tag, text or folder. On Pro, Stow transcribes audio and writes summaries and tags for you.
Text that nobody can find
- Transcripts pile up as loose files on one machine, or as rows nobody indexed.
- Finding the one you need means downloading everything first.
- Tagging hundreds of files by hand never quite happens.
How Stow handles it
Files or plain text
Upload text, markdown, CSV or JSON files, or send text straight from your code as JSON. No file needed.
Your own tags
Add tags as you upload, including key:value tags like speaker:jane or show:serial, then filter by any combination of them. Stow keeps the details you send instead of writing its own.
Transcribed and summarized on Pro
On Pro and Scale, an upload that leaves the title, description, tags and category to Stow gets analyzed: audio up to 8 MB is transcribed, and text documents get a title, summary and tags. Each app can list the fields it wants pulled out as tags, like speaker or ticker.
Search that reads what Stow wrote
Text search looks through titles, descriptions and file names, and through the summaries and transcripts Stow writes on Pro.
Private when they should be
A transcript of a private conversation shouldn’t be a public link. Upload it as private and only your own keys can read it back.
What it looks like
# Store the transcript: private, tagged by show and speaker
curl -X POST https://api.usestow.com/v1/assets \
-H "Authorization: Bearer $STOW_API_KEY" \
-F file=@episode-42.json \
-F visibility=private \
-F 'metadata={"tags":["show:serial","speaker:jane"]}'
# Later: everything Jane spoke on, in that show
curl -X POST https://api.usestow.com/v1/assets/search \
-H "Authorization: Bearer $STOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{"tags":["show:serial","speaker:jane"]}'More in the docs: Auto-detection and analysis · Searching · Private files
Questions
- Does Stow transcribe audio?
- On Pro and Scale, audio files up to 8 MB are transcribed after upload when the upload leaves the title, description, tags and category for Stow to fill in, and the transcript becomes searchable. Larger audio files are stored and described from their file name.
- Can I search the full text of my documents?
- Text search covers titles, descriptions and file names, and on Pro the summaries and transcripts Stow writes. To find documents by what’s in them on the free plan, give them descriptive titles or tags when you upload.
- Which files does Stow analyze?
- On Pro and Scale: plain text, markdown, CSV and JSON documents, audio up to 8 MB, and images up to 5 MB. Every other file is stored and found by its title, tags, folder and file name.
- Should transcripts be public?
- Usually not. Upload them with visibility set to private: they get no public link, and only your own keys can read them.
Try Stow free
The free plan holds 500 files for up to 2 apps, with no card needed. Upgrade when you want more room, or automatic transcripts, summaries and tags.
More use cases
File storage for AI agents
Give AI agents a place to store and find files. Upload with one API call or the Stow MCP server, search by tag or text, and keep private files private.
One library for several apps
Share one file library across all your apps: a key and folder per app, one API for uploads and search, duplicates stored once. Free for 2 apps.
Private file storage
Upload private files that get no public link and can only be read with your own API keys. Private by default for AI agents using the Stow MCP server.
Scrapers and data pipelines
Store what your scrapers and data pipelines collect as it arrives. Duplicates are stored once, files are tagged and foldered, and every app can search them.