SLNG Inworld Max 1.5 API

openapi: 3.0.3
info:
  title: SLNG Voice Agents Account Inworld Max 1.5 API
  version: 1.0.0
  description: 'Public API for managing Voice Agents, dispatching outbound calls, and creating web (non-telephony) sessions.


    Base URL: `https://api.agents.slng.ai`

    '
  contact:
    name: SLNG Support
    email: support@slng.ai
servers:
- url: https://api.agents.slng.ai
  description: Production
security:
- bearerAuth: []
tags:
- name: Inworld Max 1.5
  description: Inworld Max 1.5 for multilingual, expressive synthesis.
paths:
  /v1/tts/slng/inworld/max:1.5:
    post:
      operationId: slng/inworld/max:1.5
      summary: Inworld Max 1.5
      description: Synthesize speech using SLNG-hosted Inworld Max 1.5.
      tags:
      - 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:
  schemas:
    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
    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.
    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
  responses:
    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'
    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
    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'
  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
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API key