> ## Documentation Index
> Fetch the complete documentation index at: https://docs.slng.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Inworld Max 1.5
> Synthesize speech using SLNG-hosted Inworld Max 1.5.
export const HostingBanner = ({type = "slng", provider, regions = []}) => {
const isSlng = type === "slng";
const regionLabel = regions.map(r => r.toUpperCase()).join(", ");
return
{isSlng ? "SLNG Sovereign Hosting" : `3rd Party API Hosted by ${provider}`}
{isSlng ? <>
On demand in: {regionLabel}.{" "}
Request here if you want access
in any other of our 11 regions.
: <>
For SLNG Sovereign Hosting in any of our 11 regions{" "}
contact us.
}
;
};
## OpenAPI
````yaml POST /v1/tts/slng/inworld/max:1.5
openapi: 3.0.3
info:
title: SLNG Gateway API - SLNG TTS
version: 0.1.0
description: Unified API for speech-to-text and text-to-speech services.
contact:
name: SLNG Support
email: support@slng.ai
servers:
- url: https://api.slng.ai
description: Production
- url: https://stageapi.slng.ai
description: Staging
security:
- BearerAuth: []
tags:
- name: Deepgram Aura 2
description: Deepgram Aura 2 for conversational voice agents.
- name: Orpheus English
description: Orpheus TTS with emotion control.
- name: Rime Arcana v2
description: Rime Arcana v2 TTS with multi-language support.
- name: Rime Arcana v3
description: Rime Arcana v3 TTS with multilingual support (English, Hindi).
- name: Rime Coda
description: Rime Coda TTS for Bahasa Indonesian.
- name: Inworld Max 1.5
description: Inworld Max 1.5 for multilingual, expressive synthesis.
paths:
/v1/tts/slng/inworld/max:1.5:
post:
tags:
- Inworld Max 1.5
summary: Inworld Max 1.5
description: Synthesize speech using SLNG-hosted Inworld Max 1.5.
operationId: slng/inworld/max:1.5
parameters:
- $ref: '#/components/parameters/XRegionSlngInworldMax'
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/SlngInworldMaxRequest'
examples:
basic:
summary: Basic synthesis
value:
text: Hello, this is a test of Inworld text to speech.
voice: Ashley
modelId: inworld-tts-1.5-max
wordTimestamps:
summary: Request word-level timestamps
value:
text: Hello, world!
voice: Ashley
timestampType: WORD
characterTimestamps:
summary: Request character-level timestamps
value:
text: Hello world.
voice: Ashley
timestampType: CHARACTER
responses:
'200':
$ref: '#/components/responses/SlngInworldMaxSuccess'
'400':
$ref: '#/components/responses/ProviderBadRequest'
'401':
$ref: '#/components/responses/ProviderUnauthorized'
'500':
$ref: '#/components/responses/ProviderInternalServerError'
'503':
$ref: '#/components/responses/ProviderServiceUnavailable'
components:
parameters:
XRegionSlngInworldMax:
name: X-Region-Override
in: header
required: false
description: Target region override. Auto-selected if not provided.
schema:
type: string
enum:
- us-east-1
schemas:
SlngInworldMaxRequest:
type: object
description: >-
Inworld Max 1.5 synthesis request, SLNG-hosted. Audio output is
configured with flat fields (encoding, sample_rate, bit_rate,
speaking_rate) that the gateway maps to Inworld's audioConfig.
required:
- text
properties:
text:
type: string
minLength: 1
maxLength: 2000
description: Text to synthesize. Max 2,000 characters.
voice:
type: string
default: Ashley
description: >-
Inworld voice ID. Voices are multilingual — each has a native
language but can speak any supported language via the `language`
parameter (best results when `language` matches the voice's native
language). See the full catalog at
https://docs.slng.ai/voices/inworld.
modelId:
type: string
enum:
- inworld-tts-1.5-max
default: inworld-tts-1.5-max
description: ID of the Inworld TTS model.
language:
$ref: '#/components/schemas/SlngInworldMaxLanguage'
deliveryMode:
type: string
enum:
- DELIVERY_MODE_UNSPECIFIED
- STABLE
- BALANCED
- CREATIVE
description: >-
Only applies to inworld-tts-2. Controls output variation; ignored on
Max 1.5.
temperature:
type: number
minimum: 0
exclusiveMinimum: true
maximum: 2
default: 1
description: >-
Higher values produce more expressive output; lower values more
deterministic. Range (0, 2].
timestampType:
type: string
enum:
- TIMESTAMP_TYPE_UNSPECIFIED
- WORD
- CHARACTER
default: TIMESTAMP_TYPE_UNSPECIFIED
description: Controls timestamp metadata returned with the audio. Adds latency.
applyTextNormalization:
type: string
enum:
- APPLY_TEXT_NORMALIZATION_UNSPECIFIED
- 'ON'
- 'OFF'
default: APPLY_TEXT_NORMALIZATION_UNSPECIFIED
description: >-
Expands numbers, dates, and abbreviations before synthesis.
Disabling may reduce latency.
encoding:
type: string
enum:
- LINEAR16
- MP3
- OGG_OPUS
- ALAW
- MULAW
- FLAC
- PCM
- WAV
default: MP3
description: Output audio format. Maps to Inworld audioConfig.audioEncoding.
sample_rate:
type: integer
enum:
- 8000
- 16000
- 22050
- 24000
- 32000
- 44100
- 48000
default: 48000
description: >-
Output sample rate in Hz. Maps to Inworld
audioConfig.sampleRateHertz.
bit_rate:
type: integer
description: >-
Bits per second. Only applies to compressed formats (MP3, OGG_OPUS).
Maps to Inworld audioConfig.bitRate.
speaking_rate:
type: number
minimum: 0.5
maximum: 1.5
default: 1
description: >-
Playback speed. Values below 0.8 not recommended for quality. Maps
to Inworld audioConfig.speakingRate.
SlngInworldMaxLanguage:
type: string
description: >-
BCP-47 language tag specifying the language the voice should speak the
text in. Optional — when omitted, Inworld uses the voice's original
prompt and auto-detects the language from the text. Voices are
multilingual; best results when this matches the voice's native
language. These are the 15 core languages supported by
inworld-tts-1.5-max (inworld-tts-2 additionally supports ~85
experimental languages). An invalid code returns an error.
enum:
- ar-SA
- de-DE
- en-US
- es-ES
- fr-FR
- he-IL
- hi-IN
- it-IT
- ja-JP
- ko-KR
- nl-NL
- pl-PL
- pt-BR
- ru-RU
- zh-CN
SlngInworldMaxSuccessBody:
type: object
description: >-
Inworld Max 1.5 synthesis result. Inworld's native response, passed
through by the gateway.
properties:
audioContent:
type: string
format: byte
description: Base64-encoded audio in the requested encoding. Max 16MB.
usage:
type: object
description: Synthesis usage details.
properties:
processedCharactersCount:
type: integer
description: Number of input characters processed.
modelId:
type: string
description: Model used for synthesis.
timestampInfo:
type: object
description: >-
Timestamp metadata. Present only when timestampType is WORD or
CHARACTER.
properties:
wordAlignment:
type: object
description: Per-word alignment. Present when timestampType is WORD.
properties:
words:
type: array
items:
type: string
description: Aligned words in order.
wordStartTimeSeconds:
type: array
items:
type: number
description: Start time per word in seconds.
wordEndTimeSeconds:
type: array
items:
type: number
description: End time per word in seconds.
phoneticDetails:
type: array
description: >-
Per-word phoneme and viseme timing. Only available on TTS
1.5+ and TTS-2 models.
items:
type: object
properties:
wordIndex:
type: integer
description: 0-based index of the word this entry belongs to.
phones:
type: array
items:
type: object
properties:
phoneSymbol:
type: string
description: IPA phoneme symbol.
startTimeSeconds:
type: number
description: Phoneme start time in seconds.
durationSeconds:
type: number
description: Phoneme duration in seconds.
visemeSymbol:
type: string
description: >-
Viseme for lip-sync (e.g. aei, o, bmp, l, r,
qw).
isPartial:
type: boolean
description: >-
True if the word is potentially unstable (streaming
only).
characterAlignment:
type: object
description: >-
Per-character alignment. Present when timestampType is
CHARACTER.
properties:
characters:
type: array
items:
type: string
description: Aligned characters including punctuation and spaces.
characterStartTimeSeconds:
type: array
items:
type: number
description: Start time per character in seconds.
characterEndTimeSeconds:
type: array
items:
type: number
description: End time per character in seconds.
ProviderErrorResponse:
type: object
description: >
Provider error response. Contains error information from the upstream
provider.
Common errors include invalid speakers, unsupported languages, or
malformed requests.
properties:
error:
type: string
description: >-
Error type or category (e.g., "TTS service error", "Validation
error").
example: TTS service error
status:
type: number
description: >-
Original HTTP status code from the provider (may differ from gateway
response code).
example: 400
details:
type: string
description: >
Detailed error message from the provider. For TTS errors, this
typically includes
the specific validation failure (e.g., invalid speaker ID for the
selected model/language).
example: >-
Rime TTS API error: 400 Bad Request - Invalid argument: Invalid
speaker: aurelie
required:
- error
responses:
SlngInworldMaxSuccess:
description: >
Synthesis successful. Unlike other SLNG TTS models (which return raw
audio bytes), Inworld Max responds with JSON: the request is
SLNG-normalized but the response is Inworld's native body passed through
unchanged, carrying base64-encoded audio plus usage and optional
timestamp metadata.
content:
application/json:
schema:
$ref: '#/components/schemas/SlngInworldMaxSuccessBody'
examples:
basic:
summary: Synthesis result (audioContent truncated for brevity)
value:
audioContent: SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjYwLjE2LjEwMAAA
usage:
processedCharactersCount: 48
modelId: inworld-tts-1.5-max
wordTimestamps:
summary: Result with WORD timestamps (timestampType=WORD)
value:
audioContent: SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjYwLjE2LjEwMAAA
usage:
processedCharactersCount: 13
modelId: inworld-tts-1.5-max
timestampInfo:
wordAlignment:
words:
- Hello,
- world!
wordStartTimeSeconds:
- 0
- 0.51
wordEndTimeSeconds:
- 0.51
- 1.04
phoneticDetails:
- wordIndex: 0
isPartial: false
phones:
- phoneSymbol: h
startTimeSeconds: 0
durationSeconds: 0.17
visemeSymbol: aei
- phoneSymbol: ə
startTimeSeconds: 0.17
durationSeconds: 0.05
visemeSymbol: aei
- phoneSymbol: l
startTimeSeconds: 0.22
durationSeconds: 0.11
visemeSymbol: l
- phoneSymbol: oʊ1
startTimeSeconds: 0.33
durationSeconds: 0.18
visemeSymbol: o
characterTimestamps:
summary: Result with CHARACTER timestamps (timestampType=CHARACTER)
value:
audioContent: SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjYwLjE2LjEwMAAA
usage:
processedCharactersCount: 12
modelId: inworld-tts-1.5-max
timestampInfo:
characterAlignment:
characters:
- H
- e
- l
- l
- o
- w
- o
- r
- l
- d
- .
characterStartTimeSeconds:
- 0
- 0.11
- 0.21
- 0.32
- 0.42
- 0.57
- 0.66
- 0.75
- 0.84
- 0.93
- 1.02
characterEndTimeSeconds:
- 0.11
- 0.21
- 0.32
- 0.42
- 0.53
- 0.66
- 0.75
- 0.84
- 0.93
- 1.02
- 1.11
ProviderBadRequest:
description: Bad request - invalid parameters provided.
content:
application/json:
schema:
$ref: '#/components/schemas/ProviderErrorResponse'
examples:
validation-error:
summary: Validation error
value:
error: Validation error
details: 'Missing required field: text'
ProviderUnauthorized:
description: Invalid or missing API key.
content:
application/json:
schema:
$ref: '#/components/schemas/ProviderErrorResponse'
ProviderInternalServerError:
description: Internal server error from the provider.
content:
application/json:
schema:
$ref: '#/components/schemas/ProviderErrorResponse'
examples:
processing-error:
summary: Processing error
value:
error: Service error
details: Internal processing error
ProviderServiceUnavailable:
description: Service unavailable.
content:
application/json:
schema:
$ref: '#/components/schemas/ProviderErrorResponse'
securitySchemes:
BearerAuth:
type: http
scheme: bearer
description: |
API key issued by SLNG. Pass as `Authorization: Bearer `.
````