How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Wispr AI memory API

The memory API from Wispr AI — 5 operation(s) for memory.

This API exposes 5 operations across 5 paths, and defines 14 schemas. It is described by OpenAPI 3.2.0, at version 0.5.2.

Requests are made against the base URL https://api.wisprflow.ai.

5 operations 5 paths 14 schemas 2 GET3 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
0.5.2
Base URL
https://api.wisprflow.ai
Authentication
API Key, API Key
Resource Areas
1

Authentication & Security 2

Wispr AI memory API declares 2 security schemes for authenticating requests. An API key is passed in the header as Authorization (ApiKeyHeaderPatched). An API key is passed in the header as X-API-Key (APIKeyHeader).

Paths & Operations 5

Across 5 paths, the API surfaces 5 operations — 2 GET, 3 POST. Each is listed below with its method, path, parameters, and response codes.

Memory 5
POST
/api/v1/memory/ingest
Ingest a batch of ActionEvents into the voice memory system
ingest_memory body → 202422
GET
/api/v1/memory/health
Check voice-memory Graphiti connectivity
memory_health → 200
POST
/api/v1/memory/context
Return compact prompt-ready voice memory context
memory_context body → 200422
GET
/api/v1/memory/list
Debug: list the caller's raw Graphiti voice memories
list_memory 3 params → 200422
POST
/api/v1/memory/search
Debug: raw Graphiti search over the caller's voice memory
search_memory body → 200422

Schemas 14

The contract defines 14 schemas that model the data the API accepts and returns. The most detailed are ActionEnvelope (8 properties), MemoryWarmUpContext (7 properties), ValidationError (5 properties), MemoryListResponse (4 properties). Each schema is shown below with its type and property counts.

MemorySearchRequest
object
Debug request to search memory facts and nodes for a context.
3 properties
MemoryIngestResponse
object
Ingest summary: accepted/rejected counts and per-event results.
3 properties 3 required
MemorySearchResponse
object
Debug search results: the synthesized query plus matched facts and nodes.
3 properties 3 required
MemoryIngestRequest
object
Batch of action events to ingest into memory.
1 property 1 required
MemoryHealthResponse
object
Health check reporting Graphiti reachability and detail.
2 properties 1 required
HTTPValidationError
object
1 property
MemoryWarmUpContext
object
Dictation context for retrieval; the server synthesizes the Graphiti query.
7 properties
MemoryContextRequest
object
Request for a synthesized memory prompt block given dictation context.
4 properties
ActionEnvelope
object
One action event from the desktop or mobile client.
8 properties 6 required
MemoryContextResponse
object
The synthesized memory prompt block to prepend for retrieval.
1 property 1 required
IngestResultRow
object
Per-event ingest outcome, keyed by the client event id.
2 properties 2 required
AppContext
object
Identifying details of the app an action occurred in.
3 properties
MemoryListResponse
object
Debug listing of a user's memory episodes, facts, and nodes.
4 properties 4 required
ValidationError
object
5 properties 3 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

wispr-ai-memory-api-openapi.yml Raw ↑
Where this information came from

This is an independent, third-party profile of Wispr AI memory API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.