How to Use Openverse audio search in ChatGPT
Openverse audio search returns matching recordings with creator, license, attribution, and file metadata. Use it to build a shortlist from a sound description or music brief before inspecting individual tracks.
Prompts to try with Openverse audio search in ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Use Openverse audio search to find rain on a window for a podcast scene. Show the recording titles, creators, original pages, and listed licenses.
Use Openverse audio search to find acoustic guitar recordings for a classroom listening exercise. Give me a comparison table with source links and attribution.
Use Openverse audio search to look this up and give me the result as a table.
Pull the latest numbers from Openverse audio search and tell me what changed since last week.
Check Openverse audio search and summarize what you find in three bullet points.
How to set up Openverse audio search in ChatGPT
Pick the way that suits you. Each takes about two minutes.
Use the ChatGPT connector
- Add a custom MCP server
In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.
https://api.spiral.ai/mcp
- Click Connect
ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.
- Sign in to Spiral and approve
Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.
Use the Spiral skill
- Send ChatGPT this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Openverse audio search
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "alexandria", "model": "openverse-org/audio-assets/search_audio", "input": { "url": "<url>" } }'
Then paste one of the prompts above: ChatGPT finds Openverse audio search on Spiral, shows the price and runs it.
Openverse audio search providers and prices
Spiral runs Openverse audio search through Alexandria. Open a card for today's price, with every fee included.
Settings you can ask for
Ask ChatGPT for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Limit | 1 to 20 | Results per page; default 10. Anonymous access allows at most 20. | |
| Commercial use | on or off | true keeps only licences that allow commercial use (drops every NC licence). false applies no filter. | |
| Modification allowed | on or off | true keeps only licences that allow remixing (drops ND licences). false applies no filter. |
Every API field of Openverse · Search audio is on its tool page: open its card above.
What can you do with Openverse audio search in ChatGPT?
Prepare a listening shortlist for a podcast, lesson, or video with source links and draft attribution. A chat assistant can compare the returned recordings and explain which source records need review before reuse.
Build a podcast sound shortlist
Compare indexed collections, search for rain and station ambience, explore suggestions from a promising recording, and inspect the selected clips’ source links and attribution for production review.
Choose sounds for a game prototype
Review available collections, find footsteps and door sounds, explore related recordings, and assemble a candidate list with file links, creators, and licenses for review.
Prepare audio for a classroom lesson
Compare collection coverage, search for birdsong and ocean recordings, inspect related suggestions, and prepare a listening list with original source pages and draft credits.
Research a documentary sound palette
Review indexed collections, search for train and harbor sounds, explore alternatives from selected tracks, and inspect recording metadata before sending candidates to an editor.
Find replacement audio candidates
Explore suggestions from a previously selected track and run a fresh descriptive search. Inspect each candidate’s source and license before approving a replacement.
More on Openverse audio search and ChatGPT
Overview
Openverse audio search in other agents
Questions about Openverse audio search in ChatGPT
Can ChatGPT use Openverse audio search?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Openverse audio search like any built-in tool.
How much does Openverse audio search cost in ChatGPT?
$0.00873 per call. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your ChatGPT plan is separate.
Do I need an Alexandria account to use Openverse audio search in ChatGPT?
No. Spiral runs Openverse audio search on its own Alexandria account. You sign in to Spiral once and never paste a key.
How long does it take to set up Openverse audio search in ChatGPT?
About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.
Does ChatGPT wait while Openverse audio search runs?
Openverse audio search runs in the background. ChatGPT starts the run, checks on it and gives you the json when it's ready.
Does Openverse host the original recordings?
Openverse aggregates metadata for recordings hosted on third-party websites. Its audio records include the original landing page and a file URL.
Does an Openverse listing prove that I can reuse a recording?
No. Openverse explicitly says it does not verify licensing status, so the listed license must be checked against the original source before reuse.
What do the collection totals measure?
They count media items indexed by Openverse from each source. They are catalog counts, so they do not establish the complete size of a source website’s audio collection.
Can I copy the entire catalog through repeated requests?
Openverse’s terms prohibit scraping the catalog. Use the data to find and inspect recordings for a specific project.
Does the timestamp tell me when a recording was published?
The indexing timestamp tells you when Openverse indexed the media. It does not establish the recording’s original publication date.
Start using Openverse audio search in ChatGPT
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into ChatGPT:
set up https://spiral.ai/SKILL.md


