Need help with your APIs? I offer API discovery, governance & evangelism services. Explore services →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Inworld AI Text To Speech API

Synthesize speech from text using Inworld voice models.

Inworld AI Text To Speech API is one of 6 APIs that Inworld AI publishes on the APIs.io network, described by a machine-readable OpenAPI specification and an AsyncAPI event-driven specification.

This API exposes 1 JSON Schema definition.

Tagged areas include Text To Speech. The published artifact set on APIs.io includes an OpenAPI specification, API documentation, a getting-started guide, an AsyncAPI specification, a JSON-LD context, and 1 JSON Schema.

This API exposes 4 operations across 4 paths, and defines 12 schemas. It is described by OpenAPI 3.1.0, at version v1.

Requests are made against a single base URL, https://api.inworld.ai.

4 operations 4 paths 12 schemas 2 GET2 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.1.0
API Version
v1
Server
https://api.inworld.ai
Authentication
HTTP Basic
Resource Areas
1

Authentication & Security 1

Inworld AI Text To Speech API declares 1 security scheme for authenticating requests. It accepts HTTP basic authentication (BasicAuth). By default, every request must be authenticated.

Paths & Operations 4

Across 4 paths, the API surfaces 4 operations — 2 GET, 2 POST. Each is listed below with its method, path, parameters, and response codes.

Text To Speech 4

Synthesize speech from text using Inworld voice models.

POST
/tts/v1/voice
Synthesize Speech
synthesizeSpeech body → 2004XX
POST
/tts/v1/voice:stream
Stream Synthesize Speech
streamSynthesizeSpeech body → 2004XX
GET
/tts/v1/voice:websocket
WebSocket Synthesize Speech
websocketSynthesizeSpeech → 101
GET
/tts/v1/voices
List TTS Voices
listTtsVoices 1 param → 2004XX

Schemas 12

The contract defines 12 schemas that model the data the API accepts and returns. The most detailed are SynthesizeRequest (9 properties), Voice (6 properties), WordAlignment (4 properties), AudioConfig (4 properties). Each schema is shown below with its type and property counts.

PhoneticDetail
object
3 properties
AudioConfig
object
4 properties 1 required
SynthesisUsage
object
2 properties
SynthesizeStreamChunk
object
3 properties
TimestampInfo
object
2 properties
WordAlignment
object
4 properties
SynthesizeResponse
object
3 properties
Error
object
3 properties
ListVoicesResponse
object
1 property
CharacterAlignment
object
3 properties
Voice
object
6 properties
SynthesizeRequest
object
9 properties 4 required

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

inworld-ai-text-to-speech-api-openapi.yml Raw ↑

Other APIs Inworld AI publishes across the network.

Inworld LLM Router API
Inworld AI Models API
Inworld AI Realtime API
Inworld AI Speech To Text API
Inworld AI Voices API