Use with an AI assistant
These docs are built to be read by machines as well as people. Hand one URL to ChatGPT, Claude, Cursor, Copilot or anything else and it can write correct client code without you explaining the API.
The fastest way
Paste this into any chatbot:
Read https://latency.cam/llms-full.txt That is the full documentation for a voice AI API I am using. Then help me build a Hindi collections call agent.
llms-full.txt is the entire API — every endpoint, every model, every language, every caveat — as one plain-text file. It is generated from the same source of truth as the OpenAPI spec, so it cannot drift out of date.
If your tool cannot fetch URLs
Download it and paste the contents. It is deliberately plain text with no markup to trip anything up.
curl -s https://latency.cam/llms-full.txt | pbcopy
The four machine-readable endpoints
| URL | Format | Use it when |
|---|---|---|
| /llms-full.txt | text | You want an assistant to understand the whole API. Default choice. |
| /openapi.json | OpenAPI 3.1 | Generating a typed client, or your tool has native OpenAPI support (Cursor, Postman, custom GPTs). |
| /llms.txt | text | Short index. For crawlers, or when context is tight. |
Let the assistant pick the tier
There are three model tiers and the choice is short enough that an assistant does not need to look anything up: fast is the default and what every latency figure here was measured with, balanced holds longer instructions more reliably, and precise follows instructions best and is the slowest.
Voices are the same shape of question. There are 38, two per language, and the full list comes from GET /v1/models with your key — which is also what the dashboard's voice picker reads, so an assistant and a person are looking at the same thing.
One thing to tell your assistant
An assistant that has not read these docs will invent parameters, because it is pattern matching against other voice APIs. The fix is the same every time: point it at llms-full.txt and tell it to use only fields that appear there.GET /v1/config-schema is the authoritative list of every agent setting and it is generated from the engine itself, so it cannot drift from what the product accepts.