> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gengen.farm/llms.txt
> Use this file to discover all available pages before exploring further.

# Estimate voice design cost

> Estimate the final USD price for a batch of three voice previews.

Send the same body as a [Voice Design audition](https://docs.gengen.farm/api-reference/elevenlabs/voice-designs.md). An estimate requires authentication but does not generate audio, reserve balance or incur a charge.

| Audition text | Estimate |
| - | - |
| Supplied | `inputCharacters` is the Unicode character count of your text; `isMaximum` is `false`. |
| Omitted | `inputCharacters` is 1,000 and `isMaximum` is `true`. Generation reserves up to that amount and bills the actual returned text. |

`estimatedCostUsd` covers all three previews together; `pricePerThousandCharactersUsd` is the rate used.


## OpenAPI

````yaml openapi/audio.yaml POST /audio/voice-designs/estimate
openapi: 3.1.0
info:
  title: GENGEN Audio API
  version: 1.0.0
  description: >-
    Speech, dialogue, voice design, workspace voices, realtime sessions and
    completion webhooks.
servers:
  - url: https://gengen.farm/api/gengen/v1
security:
  - bearerAuth: []
paths:
  /audio/voice-designs/estimate:
    post:
      tags:
        - Voices
      summary: Estimate voice design cost
      description: >-
        Return a USD estimate for the full audition, using a maximum of 1,000
        characters when text is omitted.
      operationId: audio-estimate-voice-design
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/VoiceDesignRequest'
      responses:
        '200':
          description: Current customer price estimate.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/VoiceDesignEstimate'
        default:
          description: Request failed.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/Error'
components:
  schemas:
    VoiceDesignRequest:
      type: object
      additionalProperties: false
      required:
        - model
        - prompt
      properties:
        model:
          type: string
          enum:
            - eleven_ttv_v3
        mode:
          type: string
          enum:
            - voice_design
          default: voice_design
        prompt:
          type: string
          minLength: 20
          maxLength: 1000
          description: >-
            Voice description, measured in Unicode code points after trimming
            surrounding whitespace.
        controls:
          type: object
          additionalProperties: false
          properties:
            auditionText:
              type: string
              minLength: 100
              maxLength: 1000
              description: >-
                Optional audition text, measured in Unicode code points after
                trimming. Omit to generate text automatically with a maximum
                1000-character reservation.
            outputFormat:
              type: string
              enum:
                - mp3_44100_128
              default: mp3_44100_128
        providerOptions:
          type: object
          additionalProperties: false
          required:
            - elevenlabs
          properties:
            elevenlabs:
              type: object
              additionalProperties: false
              properties:
                seed:
                  type: integer
                  minimum: 0
                  maximum: 2147483647
                  description: >-
                    Seed for generating voice previews. Reuse it with the same
                    inputs to reproduce the voice.
                shouldEnhance:
                  type: boolean
                  default: true
                  description: Enhance the voice description before generating previews.
        webhookEndpointId:
          type: string
          format: uuid
          description: Registered completion webhook owned by the same API key.
      example:
        model: eleven_ttv_v3
        prompt: >-
          A warm, clear adult narrator with a calm delivery and a neutral
          English accent.
        controls:
          auditionText: >-
            Welcome to our quiet garden. Take a moment to breathe, enjoy the
            morning light, and imagine a fresh beginning.
    VoiceDesignEstimate:
      type: object
      required:
        - model
        - inputCharacters
        - isMaximum
        - estimatedCostUsd
        - pricePerThousandCharactersUsd
      properties:
        model:
          type: string
          enum:
            - eleven_ttv_v3
        inputCharacters:
          type: integer
          minimum: 100
          maximum: 1000
        isMaximum:
          type: boolean
          description: >-
            True when audition text is omitted and the estimate uses 1000
            characters.
        estimatedCostUsd:
          type: number
          minimum: 0
          description: >-
            Final customer estimate in USD for the entire batch of three
            previews.
        pricePerThousandCharactersUsd:
          type: number
          minimum: 0
          description: Current customer price per 1000 audition text characters.
    Error:
      type: object
      properties:
        error:
          type: object
          properties:
            code:
              type: string
            message:
              type: string
          required:
            - code
            - message
      required:
        - error
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer

````

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