Work with this as data
Every API here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for apis
7 MCP tools reach this
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.
Call it yourself
curl for this page
This API
curl "https://apis.io/api/v1/apis/kalpa-labs-meta-api"
All apis
curl "https://apis.io/api/v1/apis?limit=25"Discovery needs no key. Ratings and market analysis are Pro.
Get an API 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. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.
OpenAPI Specification
openapi: 3.2.0
info:
contact:
name: Kalpa Labs
url: https://kalpalabs.ai/
description: 'The Kalpa Speech API turns text into natural speech (**TTS**) and continues a multi-speaker
conversation as the next speaker (**converse**), returning generated text + 24 kHz audio.
**Authentication.** Every `/v1` request needs an API key, sent either as
`Authorization: Bearer <key>` (preferred) or an `X-API-Key: <key>` header.
**Rate limits.** Requests are metered per key. When you exceed your limit you receive
`429 Too Many Requests` with a `Retry-After` header; every response carries `X-RateLimit-*` headers.
**Audio.** Audio crosses the wire as base64-encoded 16-bit PCM WAV (mono, 24 kHz).
This document is the single source of truth for the contract — the docs reference, the studio''s
typed client, and the SDKs are all generated from it.
'
license:
name: Proprietary
title: Kalpa Speech Meta API
version: 0.1.0
servers:
- description: Production
url: https://api.kalpalabs.ai
- description: Local development
url: http://localhost:8080
tags:
- description: Health checks and capability discovery.
name: Meta
paths:
/health:
get:
operationId: health_health_get
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/HealthResponse'
description: Successful Response
summary: Liveness probe
tags:
- Meta
/v1/info:
get:
operationId: info_v1_info_get
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/InfoResponse'
description: Successful Response
security:
- ApiKeyAuth: []
summary: Backend info, default params, and limits
tags:
- Meta
/v1/models:
get:
operationId: models_v1_models_get
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/ModelsResponse'
description: Successful Response
security:
- ApiKeyAuth: []
summary: List available public models
tags:
- Meta
/v1/voices:
get:
operationId: voices_v1_voices_get
responses:
'200':
content:
application/json:
schema:
$ref: '#/components/schemas/VoicesResponse'
description: Successful Response
security:
- ApiKeyAuth: []
summary: List available named voices
tags:
- Meta
components:
schemas:
HealthResponse:
properties:
backend:
title: Backend
type: string
ready:
title: Ready
type: boolean
status:
default: ok
title: Status
type: string
required:
- backend
- ready
title: HealthResponse
type: object
ModelsResponse:
properties:
data:
description: The available public models.
items:
$ref: '#/components/schemas/ModelCard'
title: Data
type: array
required:
- data
title: ModelsResponse
type: object
InfoResponse:
properties:
backend:
additionalProperties: true
description: Active backend description (name, kind, sample_rate, …).
title: Backend
type: object
defaults:
additionalProperties: true
description: Default generation params.
title: Defaults
type: object
limits:
additionalProperties: true
description: Request-validation caps the gateway enforces.
title: Limits
type: object
param_schema:
description: UI metadata for the generation knobs.
items: {}
title: Param Schema
type: array
required:
- backend
- defaults
- limits
- param_schema
title: InfoResponse
type: object
VoicesResponse:
properties:
data:
description: The available named voices.
items:
$ref: '#/components/schemas/VoiceCard'
title: Data
type: array
required:
- data
title: VoicesResponse
type: object
ModelCard:
description: One public model variant, as listed by ``GET /v1/models``.
properties:
default:
default: false
description: True for the model used when `model` is omitted.
title: Default
type: boolean
description:
default: ''
description: What this model is for.
title: Description
type: string
display_name:
description: Human-readable model name.
title: Display Name
type: string
id:
description: Stable public model id used in the `model` request field.
title: Id
type: string
modes:
description: 'Supported modes: subset of ["converse", "tts"].'
items:
type: string
title: Modes
type: array
speakers:
description: Valid role labels for a turn's `speaker`, in turn order (e.g. ["0", "1"]).
items:
type: string
title: Speakers
type: array
required:
- id
- display_name
- modes
- speakers
title: ModelCard
type: object
VoiceCard:
description: One named voice, as listed by ``GET /v1/voices``.
properties:
gender:
description: Perceived voice gender.
enum:
- feminine
- masculine
title: Gender
type: string
id:
description: Stable public voice id, used as the /v1/tts/{voice_id} path segment.
title: Id
type: string
name:
description: Human-readable voice name.
title: Name
type: string
required:
- id
- name
- gender
title: VoiceCard
type: object
securitySchemes:
ApiKeyAuth:
description: 'Your Kalpa API key, sent as `Authorization: Bearer <key>` (or the `X-API-Key` header).'
scheme: bearer
type: http