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

Kalpa Labs Speech API

Text-to-speech and conversational generation.

Kalpa Labs Speech API is one of 3 APIs that Kalpa Labs publishes on the APIs.io network, described by a machine-readable OpenAPI specification and an AsyncAPI event-driven specification.

Tagged areas include Speech. The published artifact set on APIs.io includes an OpenAPI specification and an AsyncAPI specification.

This API exposes 4 operations across 4 paths, and defines 13 schemas. It is described by OpenAPI 3.2.0, at version 0.1.0.

Requests are made against 2 base URLs: https://api.kalpalabs.ai, http://localhost:8080.

4 operations 4 paths 13 schemas 4 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.2.0
API Version
0.1.0
Base URL
https://api.kalpalabs.ai
Authentication
HTTP Bearer
Contact
License
Proprietary
Resource Areas
1

Authentication & Security 1

Kalpa Labs Speech API declares 1 security scheme for authenticating requests. It accepts HTTP bearer tokens (ApiKeyAuth).

  • ApiKeyAuth — Your Kalpa API key, sent as Authorization: Bearer (or the X-API-Key header).

Paths & Operations 4

Across 4 paths, the API surfaces 4 operations — 4 POST. Each is listed below with its method, path, parameters, and response codes.

Speech 4

Text-to-speech and conversational generation.

POST
/v1/converse
Complete the open (final) turn of a conversation
converse_v1_converse_post body → 200401422429502
POST
/v1/converse/stream
Complete the open turn, streaming audio as it is generated
converse_stream_v1_converse_stream_post body → 200401422429502
POST
/v1/tts
Synthesize speech from text
tts_v1_tts_post body → 200401422429502
POST
/v1/tts/{voice_id}
Synthesize speech from text in a named voice
tts_voice_v1_tts__voice_id__post 1 param body → 200401404422429502

Schemas 13

The contract defines 13 schemas that model the data the API accepts and returns. The most detailed are GenParamsModel (7 properties), VoiceGenParamsModel (7 properties), TtsResponse (6 properties), ConverseResponse (5 properties). Each schema is shown below with its type and property counts.

ConverseReply
object
3 properties 2 required
ConverseRequest
object
Complete the open (final) turn of a conversation. Every turn except the last must carry text and/or audiowavb64 (grounded history). The last turn is the one to…
3 properties 1 required
AudioPayload
object
4 properties 3 required
VoiceTtsRequest
object
TtsRequest minus speaker (the voice determines it) with eval-default sampling. The response is a plain TtsResponse — the voice is whatever the caller put in th…
3 properties 1 required
ErrorBody
object
3 properties 2 required
ConversationTurnModel
object
3 properties
Usage
object
3 properties
ConverseResponse
object
5 properties 4 required
ErrorResponse
object
The envelope returned for every 4xx/5xx.
1 property 1 required
VoiceGenParamsModel
object
GenParamsModel with the defaults /v1/tts/{voiceid} generates under when the caller sends none — the sampling Kalpa's published side-by-side evaluations used (e…
7 properties
TtsRequest
object
4 properties 1 required
GenParamsModel
object
Generation knobs, all optional — the defaults are the tuned starting point (served with UI ranges at GET /v1/info).
7 properties
TtsResponse
object
6 properties 5 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

kalpa-labs-speech-api-openapi.yml Raw ↑

Other APIs Kalpa Labs publishes across the network.

Kalpa Labs Meta API
Kalpa Labs Usage API
Where this information came from

This is an independent, third-party profile of Kalpa Labs Speech 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.