Mengram Voice API
The Voice API from Mengram — 2 operation(s) for voice.
The Voice API from Mengram — 2 operation(s) for voice.
Every API here is available over the APIs.io API and to AI agents over MCP.
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
find_apisBrowse and filter every API in the catalog.get_api_artifactsOne API's artifacts, grouped by type.get_openapiThe primary OpenAPI for this API.find_similar_apisAPIs that look like this one.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.curl "https://apis.io/api/v1/apis/mengram-io:mengram-io-voice-api"
curl "https://apis.io/api/v1/apis?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. By signing up you are subscribing to the APIs.io and API Evangelist newsletters — you can unsubscribe from any issue. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
openapi: 3.2.0
info:
title: Mengram Voice API
description: '## Human-Like Memory for AI — Semantic + Episodic + Procedural
The only AI memory API with 3 memory types. Your AI remembers facts, events, and learned workflows.
### 3 Memory Types
- **Semantic** — facts, preferences, skills (entities, relations, knowledge graph)
- **Episodic** — events, decisions, experiences (what happened, when, outcome)
- **Procedural** — workflows, processes, habits (learned step-by-step procedures)
### Key Features
- **Cognitive Profile** — one API call generates a system prompt from all memory types
- **Unified Search** — search across all 3 types simultaneously
- **Procedure Feedback** — AI learns which workflows succeed
- **Memory Agents** — autonomous cleanup, pattern detection, weekly digests
- **Team Sharing** — shared memory across team members
- **LangChain** — drop-in replacement for ConversationBufferMemory
- **CrewAI** — 5 tools with procedural learning (agents learn optimal workflows)
- **OpenClaw** — plugin with auto-recall/capture hooks, 12 tools, and Graph RAG across all channels
### Authentication
All endpoints require `Authorization: Bearer YOUR_API_KEY` header.
### Quick Start
```python
from mengram import Mengram
m = Mengram(api_key="om-...")
m.add([{"role": "user", "content": "I use Python and Railway"}])
results = m.search_all("deployment") # semantic + episodic + procedural
profile = m.get_profile() # instant system prompt
```'
version: 2.49.0
tags:
- name: Voice
paths:
/v1/voice/vapi/recall:
post:
tags:
- Voice
summary: Vapi Recall
description: 'Vapi webhook: returns concise caller context for the AI agent.
Dispatches by message.type. Only handles `tool-calls` events; other
event types Vapi posts to the same server URL (status-update,
conversation-update, transcript, etc.) get a benign 200 response so
Vapi keeps the assistant alive rather than dropping context.
Vapi tool result MUST be a single string per
https://docs.vapi.ai/tools/custom-tools-troubleshooting — any
non-string result is silently dropped by Vapi.'
operationId: vapi_recall_v1_voice_vapi_recall_post
parameters:
- name: authorization
in: header
required: true
schema:
type: string
title: Authorization
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/VapiWebhookRequest'
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/v1/voice/vapi/save:
post:
tags:
- Voice
summary: Vapi Save
description: 'Vapi end-of-call webhook: extract memories from the transcript.
Only processes `end-of-call-report` events. Vapi streams MANY events
to the same server URL — status-update, conversation-update, partial
transcript chunks (`message.type == "transcript"`, `transcriptType:
partial`), speech-update, hang, etc. Without a type guard, the save
endpoint would re-run extraction on every partial transcript chunk
(dozens of times per call), burning quota and creating duplicate
memory entries. The guard makes all other events benign no-ops.
For end-of-call-report the final transcript lives at
`message.transcript` AND `message.artifact.transcript` per
https://github.com/VapiAI/docs/blob/main/fern/server-url/events.mdx.
We read whichever is present.'
operationId: vapi_save_v1_voice_vapi_save_post
parameters:
- name: authorization
in: header
required: true
schema:
type: string
title: Authorization
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/VapiWebhookRequest'
responses:
'200':
description: Successful Response
content:
application/json:
schema: {}
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
components:
schemas:
VapiWebhookRequest:
properties:
message:
$ref: '#/components/schemas/_VapiWebhookMessage'
type: object
required:
- message
title: VapiWebhookRequest
_VapiWebhookMessage:
properties:
type:
anyOf:
- type: string
- type: 'null'
title: Type
toolCalls:
anyOf:
- items:
additionalProperties: true
type: object
type: array
- type: 'null'
title: Toolcalls
toolCallList:
anyOf:
- items:
additionalProperties: true
type: object
type: array
- type: 'null'
title: Toolcalllist
call:
anyOf:
- $ref: '#/components/schemas/_VapiCall'
- type: 'null'
transcript:
anyOf:
- type: string
- type: 'null'
title: Transcript
artifact:
anyOf:
- additionalProperties: true
type: object
- type: 'null'
title: Artifact
transcriptType:
anyOf:
- type: string
- type: 'null'
title: Transcripttype
type: object
title: _VapiWebhookMessage
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
_VapiCustomer:
properties:
number:
anyOf:
- type: string
- type: 'null'
title: Number
type: object
title: _VapiCustomer
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
input:
title: Input
ctx:
type: object
title: Context
type: object
required:
- loc
- msg
- type
title: ValidationError
_VapiCall:
properties:
customer:
anyOf:
- $ref: '#/components/schemas/_VapiCustomer'
- type: 'null'
id:
anyOf:
- type: string
- type: 'null'
title: Id
type:
anyOf:
- type: string
- type: 'null'
title: Type
type: object
title: _VapiCall