conversations
List conversations
Returns conversations the API key's user can see, ordered by
created_at descending (newest first). Each list entry contains a
short summary and source metadata (no source content). Call
GET /conversations/{id} to fetch the full payload including
source content.
GET
/api/v1/conversations Query parameters
| limit integer | Page size (max 100). |
| cursor string | Cursor returned from a previous list response. |
| folder_id string | Restrict to conversations in this folder. By default this includes any descendant subfolder; pass recursive=false for direct children only. |
| recursive boolean | When folder_id is set, controls whether descendants are included. Default true (any depth); set false to limit to conversations whose immediate folder is folder_id. |
| status "ready" · "pending" · "error" · "all" | Filter by status. Defaults to ready so that polling integrations
don't see in-progress or failed conversations. Pass all to
include every status.
|
| created_after string · date-time | Only return conversations created strictly after this timestamp.
Use the created_at of the newest conversation from your previous
sync as the next value. ISO 8601.
|
Response fields
| data array of object | |
| ↳id string | |
| ↳title string · nullable | |
| ↳created_at string · date-time | When the conversation was created in Klang. Use this as the
next created_after value for incremental sync.
|
| ↳updated_at string · date-time | |
| ↳status "pending" · "ready" · "error" · nullable | Processing state. Wait for ready before reading summary
or transcript content.
|
| ↳folder_id string · nullable | ID of the immediate folder containing the conversation. null
for conversations at the workspace root.
|
| ↳digest string · nullable | AI-generated short summary (≤80 characters) with the key names and topics, optimised to distinguish this conversation from similar ones. Present in both list and retrieve responses. |
| ↳sources array of object | A piece of input attached to a conversation. Klang's summary and
analysis are derived from the conversation's full set of sources —
so this is what you read when you want to see what the AI was
working from. Most conversations have a transcript as their
primary source plus any extras the user attached. List responses
return this minimal shape; use GET /conversations/{id} for the
full version with title, added_at, content, and
participants.
|
| ↳id string | |
| ↳type "transcript" · "document" · "text" · "file" | What kind of input this source is.
- transcript — what was said in a recorded meeting. The full
speaker-labeled, time-stamped text is in content (on
Source).
- document — a document authored inside Klang (agendas,
notes, decision logs, etc.).
- text — a snippet of plain text the user pasted into the
conversation.
- file — an uploaded file (PDF, slide deck, Word doc).
Extracted plain text is in content.
|
| ↳duration_seconds integer · nullable | Recording length. null for non-transcript sources. |
| ↳language string · nullable | ISO 639-3 code (e.g. eng, swe). null for non-transcript sources. |
| next_cursor string · nullable | |
| has_more boolean |