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

# PDF to Text

> Convert PDF and scanned images to text with layout preserved. This method uses OCR and reporoduces layout.



## OpenAPI

````yaml /openapi.json post /v1/pdf/convert/to/text
openapi: 3.0.1
info:
  title: PDF.co API
  description: ''
  version: '1.0'
servers:
  - url: https://api.pdf.co
security:
  - ApiKeyAuth: []
tags:
  - name: Extraction
  - name: Editing
  - name: PDF Conversion
  - name: Excel Conversion
  - name: PDF Merging & Splitting
  - name: Forms
  - name: Find & Search
  - name: Document, File & System
  - name: Pages
  - name: Barcodes
paths:
  /v1/pdf/convert/to/text:
    post:
      tags:
        - PDF Conversion
      summary: PDF to Text
      description: >-
        Convert PDF and scanned images to text with layout preserved. This
        method uses OCR and reporoduces layout.
      operationId: post_v1_pdf_convert_to_text
      requestBody:
        content:
          application/json:
            schema:
              type: object
              properties:
                url:
                  allOf:
                    - $ref: '#/components/schemas/url'
                  default: >-
                    https://pdfco-test-files.s3.us-west-2.amazonaws.com/pdf-to-text/sample.pdf
                lang:
                  $ref: '#/components/schemas/lang'
                rect:
                  $ref: '#/components/schemas/rect'
                unwrap:
                  $ref: '#/components/schemas/unwrap'
                linegrouping:
                  $ref: '#/components/schemas/linegrouping'
                inline:
                  allOf:
                    - $ref: '#/components/schemas/inline'
                  default: true
                pages:
                  $ref: '#/components/schemas/pages0'
                file:
                  $ref: '#/components/schemas/file'
                name:
                  $ref: '#/components/schemas/name'
                async:
                  allOf:
                    - $ref: '#/components/schemas/async'
                  default: false
                password:
                  $ref: '#/components/schemas/password'
                timeout:
                  $ref: '#/components/schemas/timeout'
                expiration:
                  $ref: '#/components/schemas/expiration'
                profiles:
                  $ref: '#/components/schemas/profiles'
                httpusername:
                  $ref: '#/components/schemas/httpusername'
                httppassword:
                  $ref: '#/components/schemas/httppassword'
              additionalProperties: false
              required:
                - url
        required: false
      responses:
        '200':
          $ref: '#/components/responses/Success'
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '402':
          $ref: '#/components/responses/NotEnoughCredits'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
        '408':
          $ref: '#/components/responses/Timeout'
        '429':
          $ref: '#/components/responses/TooManyRequests'
        '441':
          $ref: '#/components/responses/InvalidPassword'
        '442':
          $ref: '#/components/responses/DamagedDocument'
        '443':
          $ref: '#/components/responses/PermissionsError'
        '444':
          $ref: '#/components/responses/ProfilesParsingError'
        '445':
          $ref: '#/components/responses/TimeoutError'
        '446':
          $ref: '#/components/responses/MissingFiles'
        '447':
          $ref: '#/components/responses/InvalidTemplate'
        '448':
          $ref: '#/components/responses/InvalidUrlOrHtml'
        '449':
          $ref: '#/components/responses/InvalidIndexRange'
        '450':
          $ref: '#/components/responses/InvalidPageRange'
        '452':
          $ref: '#/components/responses/InvalidUrl'
        '454':
          $ref: '#/components/responses/InvalidParameters'
        '500':
          $ref: '#/components/responses/InternalServerError'
components:
  schemas:
    url:
      type: string
      format: uri
      description: >-
        URL to the source file [`url`
        attribute](/api-reference/url-input-and-request-limits).
    lang:
      type: string
      description: >-
        Set the language for OCR (text from image) to use for scanned PDF, PNG,
        and JPG documents input when extracting text. see [Language
        Support](/api-reference/language-support). You can also use 2 languages
        simultaneously like this: `eng+deu` (any combination).
      pattern: ^[a-z]{3}(\+[a-z]{3})*$
      default: eng
      example: eng+deu
    rect:
      type: string
      format: '{x} {y} {width} {height}'
      description: >-
        Defines coordinates for extraction. Use[PDF Edit Add
        Helper](https://app.pdf.co/pdf-edit-add-helper) to get or measure PDF
        coordinates. The format is `{x} {y} {width} {height}`.
      example: 10 20 300 400
    unwrap:
      type: boolean
      default: false
      description: >-
        Unwrap lines into a single line within table cells in provided PDF
        documents. This is only applicable when `lineGrouping` is set to `1`.
    linegrouping:
      type: string
      pattern: ^[123]$
      enum:
        - '1'
        - '2'
        - '3'
      description: >-
        Controls how lines of text are grouped when extracting data from a PDF.
        Line grouping within table cells. The available modes are: `1`, `2`,
        `3`. For more information, see [Line Grouping](#line-grouping-options).
    inline:
      default: false
      type: boolean
      description: >-
        Set to true to return results inside the response. Otherwise, the
        endpoint will return a URL to the output file generated.
    pages0:
      type: string
      description: >-
        Page indices/ranges (0-based). Items are comma-separated. Each item is
        one of: N (e.g., 0), N-M (e.g., 3-7), N- (open-ended, e.g., 10-), or !N
        (reverse index; !0 is last page, !1 is second-to-last). Whitespace is
        allowed. If not specified, the default configuration processes all
        pages.
      pattern: >-
        ^\s*(?:!?\d+\s*-\s*!?\d+|!?\d+\s*-\s*|!?\d+)\s*(?:,\s*(?:!?\d+\s*-\s*!?\d+|!?\d+\s*-\s*|!?\d+)\s*)*$
      example: 0,2,5-10, !0, !5-!2
    file:
      type: string
      format: path to a local file
      description: The path to the local file to be uploaded.
      readOnly: true
    name:
      type: string
      description: File name for generated output.
    async:
      type: boolean
      default: false
      description: >-
        Set `async` to `true` for long processes to run in the background, API
        will then return a `jobId` which you can use with the [Background Job
        Check endpoint](/api-reference/job-check). Also see [Webhooks &
        Callbacks](/api-reference/webhooks)
    password:
      type: string
      description: Password for the PDF file.
    timeout:
      type: number
      description: Timeout for output links in seconds
      readOnly: true
    expiration:
      type: number
      default: 60
      description: >-
        Sets the expiration time for the output link, in minutes. After this
        period, generated output file(s) are automatically deleted from [PDF.co
        Temporary Files Storage](/api-reference/file-upload/overview). The
        maximum allowed duration depends on your subscription plan. For
        permanent storage of input files (e.g., reusable images, PDF templates,
        documents), use `PDF.co Built‑In Files Storage`.
    profiles:
      type: string
      description: >-
        Profiles are used configure extra options for specific API endpoints and
        may be unique to an API. For more information, see
        [Profiles](/api-reference/profiles) and the documentation of each
        endpoint for profiles specific to it.
    httpusername:
      type: string
      description: HTTP auth user name if required to access source URL.
    httppassword:
      type: string
      description: HTTP auth password if required to access source URL.
  responses:
    Success:
      description: Success.
      content:
        application/json:
          schema:
            type: object
            properties:
              status:
                type: string
                example: success
                description: Status of the API response.
              message:
                type: string
                example: Success
                description: Descriptive message for the response status.
              url:
                type: string
                format: uri
                example: https://pdf-temp-files.s3.us-west-2.amazonaws.com/output.pdf
                description: URL to the output file.
              jobId:
                type: string
                example: 6YSZD3U872ZYYFEDMQCQSGEEO8YSF5WA
                description: Unique identifier for the job.
              credits:
                type: integer
                example: 2
                description: Credits used for this operation.
              remainingCredits:
                type: integer
                example: 1480582
                description: Credits remaining after this operation.
              duration:
                type: integer
                example: 33
                description: Time taken to complete the request, in milliseconds.
    BadRequest:
      description: >-
        Bad request. Typically due to bad input parameters or unreachable input
        URLs (e.g., access restrictions like login or password).
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 400
              message:
                type: string
                example: >-
                  Bad request. Typically due to bad input parameters or
                  unreachable input URLs (e.g., access restrictions like login
                  or password).
    Unauthorized:
      description: >-
        Unauthorized. Authentication is required and has failed or has not yet
        been provided.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 401
              message:
                type: string
                example: >-
                  Unauthorized. Authentication is required and has failed or has
                  not yet been provided.
    NotEnoughCredits:
      description: Not enough credits.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 402
              message:
                type: string
                example: Not enough credits.
    Forbidden:
      description: Access forbidden for input URL.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 403
              message:
                type: string
                example: Access forbidden for input URL.
    NotFound:
      description: The requested resource could not be found.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 404
              message:
                type: string
                example: The requested resource could not be found.
    Timeout:
      description: The server timed out waiting for the request.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 408
              message:
                type: string
                example: The server timed out waiting for the request.
    TooManyRequests:
      description: Too many requests in a given time period.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 429
              message:
                type: string
                example: Too many requests in a given time period.
    InvalidPassword:
      description: Invalid Password. Password protected document.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 441
              message:
                type: string
                example: Invalid Password. Password protected document.
    DamagedDocument:
      description: Input document is damaged or of incorrect type.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 442
              message:
                type: string
                example: Input document is damaged or of incorrect type.
    PermissionsError:
      description: >-
        Permissions. The operation is prohibited by document security settings.
        You can turn off this check by setting the `profiles` param to
        `{CheckPermissions: false}`. Important: only use this if you are the
        owner or have legal permission.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 443
              message:
                type: string
                example: >-
                  Permissions. The operation is prohibited by document security
                  settings.
    ProfilesParsingError:
      description: >-
        Profiles parsing error. Please ensure that the configuration is
        supported. See `/profiles` samples.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 444
              message:
                type: string
                example: >-
                  Profiles parsing error. Please ensure that the configuration
                  is supported.
    TimeoutError:
      description: >-
        Timeout error. For large documents, use asynchronous mode (`async=true`)
        and check status via `/job/check`. For many-page files, use the `pages`
        parameter.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 445
              message:
                type: string
                example: >-
                  Timeout error. For large documents, use asynchronous mode
                  (async=true) and check status via /job/check.
    MissingFiles:
      description: Some files required for conversion are missing.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 446
              message:
                type: string
                example: Some files required for conversion are missing.
    InvalidTemplate:
      description: Invalid template.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 447
              message:
                type: string
                example: Invalid template.
    InvalidUrlOrHtml:
      description: Invalid URL or HTML. Ensure the provided URL is valid and accessible.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 448
              message:
                type: string
                example: >-
                  Invalid URL or HTML. Ensure the provided URL is valid and
                  accessible.
    InvalidIndexRange:
      description: >-
        Invalid index range. Page index is out of range. Use `/pdf/info` to get
        page count. First page is `0`.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 449
              message:
                type: string
                example: Invalid index range. Page index is out of range.
    InvalidPageRange:
      description: Invalid page range specified.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 450
              message:
                type: string
                example: Invalid page range specified.
    InvalidUrl:
      description: Invalid URL.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 452
              message:
                type: string
                example: Invalid URL.
    InvalidParameters:
      description: Invalid parameters.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 454
              message:
                type: string
                example: Invalid parameters.
    InternalServerError:
      description: Something went wrong. Please try again or contact support.
      content:
        application/json:
          schema:
            type: object
            properties:
              error:
                type: boolean
                example: true
              status:
                type: integer
                example: 500
              message:
                type: string
                example: Something went wrong. Please try again or contact support.
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: x-api-key

````