> ## 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.

# Gradium TTS

> Real-time multilingual text-to-speech with streaming WebSocket and one-shot HTTP synthesis

**Hosting: routed through SLNG (Gradium).** This model runs on Gradium's servers; SLNG proxies each request through the nearest regional gateway. Available in Netherlands, Germany, United Kingdom, Israel, South Africa. Send requests to your region's gateway base URL: `https://eu-north.api.slng.ai`, `https://eu-west.api.slng.ai`, `https://gb.api.slng.ai`, `https://il.api.slng.ai`, `https://za.api.slng.ai`.


## OpenAPI

````yaml api-reference/openapi/tts-gradium.oas.yaml POST /v1/tts/gradium/tts:default
openapi: 3.0.3
info:
  title: SLNG Gateway API - Gradium TTS
  version: 0.1.0
  description: >-
    Real-time multilingual text-to-speech with streaming WebSocket and one-shot
    HTTP synthesis
  contact:
    name: SLNG Support
    email: support@slng.ai
servers:
  - url: https://eu-north.api.slng.ai
    description: 'Regional gateway: European Union (North) (eu-north)'
  - url: https://eu-west.api.slng.ai
    description: 'Regional gateway: European Union (West) (eu-west)'
  - url: https://gb.api.slng.ai
    description: 'Regional gateway: United Kingdom (gb)'
  - url: https://il.api.slng.ai
    description: 'Regional gateway: Israel (il)'
  - url: https://za.api.slng.ai
    description: 'Regional gateway: South Africa (za)'
security:
  - BearerAuth: []
tags:
  - name: Gradium TTS
    description: >-
      Real-time multilingual text-to-speech with streaming WebSocket and
      one-shot HTTP synthesis.
paths:
  /v1/tts/gradium/tts:default:
    post:
      tags:
        - Gradium TTS
      summary: Gradium TTS default
      description: >-
        Real-time multilingual text-to-speech with streaming WebSocket and
        one-shot HTTP synthesis
      operationId: gradium/tts:default
      requestBody:
        $ref: '#/components/requestBodies/GradiumTtsDefaultRequestBody'
      responses:
        '200':
          description: Success
        '400':
          $ref: '#/components/responses/ProviderBadRequest'
        '401':
          $ref: '#/components/responses/ProviderUnauthorized'
        '500':
          $ref: '#/components/responses/ProviderInternalServerError'
        '503':
          $ref: '#/components/responses/ProviderServiceUnavailable'
components:
  requestBodies:
    GradiumTtsDefaultRequestBody:
      required: true
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/GradiumTtsDefaultRequest'
          examples:
            example1:
              summary: Basic synthesis
              value:
                text: Hello, this is a test of Gradium text to speech.
                voice_id: YTpq7expH9539ERJ
                output_format: wav
  responses:
    ProviderBadRequest:
      description: Bad request — invalid parameters.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: string
    ProviderUnauthorized:
      description: Unauthorized — invalid or missing API key.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: string
    ProviderInternalServerError:
      description: Internal server error.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: string
    ProviderServiceUnavailable:
      description: Service temporarily unavailable.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: string
  schemas:
    GradiumTtsDefaultRequest:
      type: object
      properties:
        text:
          type: string
          minLength: 1
          description: Text to synthesize.
        voice_id:
          type: string
          description: Voice ID from the Gradium voice library or a custom voice ID.
        output_format:
          type: string
          description: Output audio format.
          enum:
            - wav
            - pcm
            - pcm_8000
            - pcm_16000
            - pcm_24000
            - opus
            - ulaw_8000
            - alaw_8000
          default: wav
        encoding:
          type: string
          description: SLNG normalized output audio encoding (WebSocket streaming).
          default: wav
          enum:
            - wav
            - linear16
            - pcm
            - opus
            - mulaw
            - alaw
        language:
          type: string
          description: Language hint for synthesis.
          default: en
          enum:
            - en
            - fr
            - de
            - es
            - pt
        temperature:
          type: number
          description: Sampling temperature (stability). Lower is more stable.
          minimum: 0
          maximum: 1.4
        only_audio:
          type: boolean
          description: >-
            HTTP only. When true, returns raw audio bytes instead of a JSON
            message stream.
          default: true
      required:
        - text
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer

````