Metadata backlogs
A deep library with thin descriptions is a library nobody discovers.
For studios, publishers and media apps
Stories travel further with better metadata
Episode synopses, script coverage, content tags, localisation first passes and audience copy. Let models handle the volume so your creative team keeps the craft.
Rich metadata
synopses and tags for every title
Faster coverage
first-read notes on submissions
Clear cost
price on every generated asset
The problem
What is slowing you down today
The submissions pile
Readers cannot keep up, and great scripts wait months for a first look.
Localisation bottlenecks
Every market needs its own synopsis, tagline and promo copy.
Capabilities
Everything you need, nothing you don't
Synopses at every length
Logline, short and long synopsis from a script or episode transcript in one call.
Content tagging
Genre, mood, themes and audience tags as structured output for your catalog.
Coverage notes
A first-pass summary of premise, structure and characters for a reader to build on.
Localisation drafts
First-pass taglines and descriptions for each market, for native editors to polish.
Cache for repeat titles
Identical prompts inside the cache window come back instantly and are not billed.
One endpoint for your apps
Power in-app recaps and recommendations copy from your backend.
Use cases
What teams run on it
01
Library enrichment
Fresh synopses and tags for back-catalog titles.
02
Script coverage
First-read notes to help readers prioritise.
03
Episode recaps
Previously-on summaries for apps and newsletters.
04
Promo copy
Taglines and social copy for launches across markets.
How it works
From sign-up to production
- 1
Test on one title
Generate synopses and tags in the playground.
- 2
Batch the library
Loop through titles with an API key and Idempotency-Key per item.
- 3
Ship to your apps
Call the endpoint from your backend for live features.
Control
Built so you stay in charge
Keys you control
API keys are shown once at creation and stored only as a hash. Revoke any key instantly from Settings.
Spend you can see
Every request carries its own receipt: tokens in, tokens out, latency and price. Nothing is billed that you cannot trace.
Limits you set
Per-account rate limits and a free monthly allowance keep experiments safe before they become production.
Data you decide on
You choose exactly what you send. Repeat prompts can be served from your cache, and cache hits are never billed.
For developers
One endpoint. Every model.
Send a prompt and a capability, or name a model. One bearer key, one small JSON body, and a full receipt on every response.
curl https://YOUR-DOMAIN/api/ainf/inference \
-H "Authorization: Bearer $AI_INFERENCE_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: order-1042" \
-d '{"prompt":"Summarise this ticket in one line","capability":"chat"}'Questions, answered
Can it handle full scripts?
Send the script text in the prompt. Very long scripts work best split into acts or scenes.
Will it replace our readers and editors?
No. It gives them a strong first pass so they can spend their time on judgment and taste.
Who owns the output?
Output belongs to your account to use as you choose. Check rights for any source material you send.
How is it priced?
Per token at the price listed for each model, after a free monthly allowance.
Let your whole library be found
Enrich your first titles on the free allowance.