> ## 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.

# Aura 2

> Synthesize speech using Deepgram Aura 2 for conversational voice agents.

**Hosting: routed through SLNG (Deepgram).** This model runs on Deepgram's servers; SLNG proxies each request through the regional gateway you call. Available in Netherlands, Germany, United States (East, West), Australia, United Kingdom, India. Send requests to your region's gateway base URL: `https://eu-north.api.slng.ai`, `https://eu-west.api.slng.ai`, `https://us-east.api.slng.ai`, `https://us-west.api.slng.ai`, `https://au.api.slng.ai`, `https://gb.api.slng.ai`, `https://in.api.slng.ai`.


## OpenAPI

````yaml api-reference/openapi/tts-deepgram.oas.yaml POST /v1/tts/deepgram/aura:2
openapi: 3.0.3
info:
  title: SLNG Gateway API - Deepgram 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://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://us-east.api.slng.ai
    description: 'Regional gateway: United States (East) (us-east)'
  - url: https://us-west.api.slng.ai
    description: 'Regional gateway: United States (West) (us-west)'
  - url: https://au.api.slng.ai
    description: 'Regional gateway: Australia (au)'
  - url: https://gb.api.slng.ai
    description: 'Regional gateway: United Kingdom (gb)'
  - url: https://in.api.slng.ai
    description: 'Regional gateway: India (in)'
security:
  - BearerAuth: []
tags:
  - name: Deepgram Aura 2
    description: Deepgram Aura 2 for conversational voice agents.
paths:
  /v1/tts/deepgram/aura:2:
    post:
      tags:
        - Deepgram Aura 2
      summary: Aura 2
      description: Synthesize speech using Deepgram Aura 2 for conversational voice agents.
      operationId: deepgram/aura:2
      requestBody:
        $ref: '#/components/requestBodies/DeepgramAura2TtsRequestBody'
      responses:
        '200':
          $ref: '#/components/responses/TtsSynthesisSuccess'
        '400':
          $ref: '#/components/responses/ProviderBadRequest'
        '401':
          $ref: '#/components/responses/ProviderUnauthorized'
        '500':
          $ref: '#/components/responses/ProviderInternalServerError'
        '503':
          $ref: '#/components/responses/ProviderServiceUnavailable'
components:
  requestBodies:
    DeepgramAura2TtsRequestBody:
      required: true
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/DeepgramAura2TtsRequest'
          examples:
            english:
              summary: Basic synthesis
              value:
                model: aura-2-thalia-en
                text: Hello, this is a test of text to speech synthesis.
            spanish:
              summary: Spanish synthesis
              value:
                model: aura-2-celeste-es
                text: Hola, esto es una prueba de síntesis de texto a voz.
  responses:
    TtsSynthesisSuccess:
      description: Synthesis successful.
      content:
        audio/*:
          schema:
            $ref: '#/components/schemas/AudioBinary'
    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'
  schemas:
    DeepgramAura2TtsRequest:
      allOf:
        - $ref: '#/components/schemas/DeepgramAuraTtsRequestBase'
        - type: object
          properties:
            model:
              $ref: '#/components/schemas/DeepgramAura2ModelName'
    AudioBinary:
      type: string
      format: binary
      description: Binary audio data.
    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
    DeepgramAuraTtsRequestBase:
      type: object
      properties:
        text:
          $ref: '#/components/schemas/TextToSynthesize'
        encoding:
          $ref: '#/components/schemas/DeepgramTtsEncoding'
        sample_rate:
          $ref: '#/components/schemas/DeepgramTtsSampleRate'
        container:
          $ref: '#/components/schemas/DeepgramTtsContainer'
        bit_rate:
          type: integer
          description: >-
            Output bit rate for lossy encodings only. `mp3` accepts 8000, 16000,
            24000, 32000, and 48000 (the MP3 sample rate is derived from it,
            e.g. 48000 bps yields 24000 Hz); `opus` accepts every listed value.
            Must be omitted for other encodings.
          enum:
            - 8000
            - 16000
            - 24000
            - 32000
            - 48000
            - 64000
            - 96000
            - 128000
            - 192000
            - 256000
      required:
        - text
    DeepgramAura2ModelName:
      type: string
      description: >-
        Voice model name. Check the full list with audio samples in the [voice
        list](https://developers.deepgram.com/docs/tts-models).
      enum:
        - aura-2-amalthea-en
        - aura-2-andromeda-en
        - aura-2-apollo-en
        - aura-2-arcas-en
        - aura-2-aries-en
        - aura-2-asteria-en
        - aura-2-athena-en
        - aura-2-atlas-en
        - aura-2-aurora-en
        - aura-2-callista-en
        - aura-2-cordelia-en
        - aura-2-cora-en
        - aura-2-delia-en
        - aura-2-draco-en
        - aura-2-electra-en
        - aura-2-harmonia-en
        - aura-2-helena-en
        - aura-2-hera-en
        - aura-2-hermes-en
        - aura-2-hyperion-en
        - aura-2-iris-en
        - aura-2-janus-en
        - aura-2-juno-en
        - aura-2-jupiter-en
        - aura-2-luna-en
        - aura-2-mars-en
        - aura-2-minerva-en
        - aura-2-neptune-en
        - aura-2-odysseus-en
        - aura-2-ophelia-en
        - aura-2-orion-en
        - aura-2-orpheus-en
        - aura-2-pandora-en
        - aura-2-phoebe-en
        - aura-2-pluto-en
        - aura-2-saturn-en
        - aura-2-selene-en
        - aura-2-thalia-en
        - aura-2-theia-en
        - aura-2-vesta-en
        - aura-2-zeus-en
        - aura-2-agustina-es
        - aura-2-alvaro-es
        - aura-2-antonia-es
        - aura-2-aquila-es
        - aura-2-carina-es
        - aura-2-celeste-es
        - aura-2-diana-es
        - aura-2-estrella-es
        - aura-2-gloria-es
        - aura-2-javier-es
        - aura-2-luciano-es
        - aura-2-nestor-es
        - aura-2-olivia-es
        - aura-2-selena-es
        - aura-2-silvia-es
        - aura-2-sirio-es
        - aura-2-valerio-es
        - aura-2-beatrix-nl
        - aura-2-cornelia-nl
        - aura-2-daphne-nl
        - aura-2-hestia-nl
        - aura-2-lars-nl
        - aura-2-leda-nl
        - aura-2-rhea-nl
        - aura-2-roman-nl
        - aura-2-sander-nl
        - aura-2-agathe-fr
        - aura-2-hector-fr
        - aura-2-aurelia-de
        - aura-2-elara-de
        - aura-2-fabian-de
        - aura-2-julius-de
        - aura-2-kara-de
        - aura-2-lara-de
        - aura-2-viktoria-de
        - aura-2-cesare-it
        - aura-2-cinzia-it
        - aura-2-demetra-it
        - aura-2-dionisio-it
        - aura-2-elio-it
        - aura-2-flavio-it
        - aura-2-livia-it
        - aura-2-maia-it
        - aura-2-melia-it
        - aura-2-perseo-it
        - aura-2-ama-ja
        - aura-2-ebisu-ja
        - aura-2-fujin-ja
        - aura-2-izanami-ja
        - aura-2-uzume-ja
      default: aura-2-thalia-en
    TextToSynthesize:
      type: string
      minLength: 1
      description: Text to synthesize.
    DeepgramTtsEncoding:
      type: string
      description: >-
        Output audio encoding for HTTP synthesis (default linear16). Parameter
        applicability depends on the encoding and Deepgram rejects a parameter
        that does not apply: `sample_rate` does not apply to `mp3` or `opus`,
        `container` does not apply to `mp3` or `flac`, and `bit_rate` applies
        only to `mp3` and `opus`. `flac` accepts every sample rate except 24000.
        `aac` is not offered because its raw stream cannot be metered. Over
        WebSocket the same Aura models accept only `linear16`, `mulaw`, and
        `alaw`.
      enum:
        - linear16
        - mp3
        - opus
        - flac
        - mulaw
        - alaw
      default: linear16
    DeepgramTtsSampleRate:
      type: integer
      description: >-
        Output sample rate in Hz. Applies to `linear16` (all values, default
        24000), `mulaw`/`alaw` (8000 or 16000), and `flac` (8000, 16000, 32000,
        48000; 24000 is rejected, default 48000). Must be omitted for `mp3` and
        `opus`.
      enum:
        - 8000
        - 16000
        - 24000
        - 32000
        - 48000
      default: 24000
    DeepgramTtsContainer:
      type: string
      description: >-
        Output container. `none` or `wav` for `linear16`, `mulaw`, and `alaw`
        (default `wav`); `ogg` only for `opus`. Must be omitted for `mp3` and
        `flac`.
      enum:
        - none
        - wav
        - ogg
      default: wav
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: |
        API key issued by SLNG. Pass as `Authorization: Bearer <token>`.

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.