Skip to main content
AiGenda turns a meeting recording into a protocol: what was agreed, who owns what, and who said what. The API does the same thing as the web cabinet, but from your own system: you upload a recording, start processing, and fetch the result.

​
How a recording flows through the API

1
Token
POST /api/token/
Sign in with your AiGenda email and password
2
Space
GET /api/spaces/
Pick where recordings live and whose plan pays for the minutes
3
Upload
POST …/audio/
As a file, by URL, from YouTube, or with a meeting bot
4
Processing
POST /api/audio/classify/
Start it and poll the status
5
Result
GET …/result/
Markdown protocol, utterance-level transcript, source file

Quickstart

Your first protocol in six curl requests.

Upload methods

File, URL, YouTube, or a meeting bot.

Result structure

What the protocol and transcript contain.

Full example

A Python script from sign-in to the finished protocol.

​
What you need

  • An AiGenda account with a password. If you sign in to the cabinet with Google, set a password on the password recovery page.
  • Minutes on your plan. Processing charges minutes by recording length. You can see the balance in the cabinet and in the API, see Spaces and minutes.
Create a separate account for the integration and invite it to the space you need. The integration then doesn’t depend on one employee’s password, and recordings from the API are easy to tell apart in the cabinet.
Building the integration with an AI agent? Give it the full documentation in one file and the ready-made prompt from Integrating with an AI agent.
Last modified on October 17, 2026