> For clean Markdown of any page, append `.md` to the page URL.
> For a complete documentation index, see https://docs.sarvam.ai/llms.txt.
> For full documentation content in one file, see https://docs.sarvam.ai/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server.

# Digitise Document

POST https://api.sarvam.ai/doc-ai/v1/job/digitise
Content-Type: multipart/form-data

Creates and starts a digitise job from files or pre-uploaded handles. Digitise converts documents into structured HTML or Markdown while preserving layout.

**Input:** Exactly one of `file` and `upload_ids` must be provided. Use `POST /doc-ai/v1/job/upload` to obtain upload IDs.

**Processing:** the job runs asynchronously. Poll `GET /doc-ai/v1/job/{job_id}/status` until a terminal status (`completed`, `partially_completed`, `failed`, `rejected`), then fetch output via the results or download-url endpoints.

Digitise JSON results include blocks with text, tag and bounding box.

Reference: https://docs.sarvam.ai/api-reference/doc-ai/job/digitise

## OpenAPI Specification

```yaml
openapi: 3.1.0
info:
  title: sarvam
  version: 1.0.0
paths:
  /doc-ai/v1/job/digitise:
    post:
      operationId: digitise
      summary: Create Document AI Digitise Job
      description: >-
        Creates and starts a digitise job from files or pre-uploaded handles.
        Digitise converts documents into structured HTML or Markdown while
        preserving layout.


        **Input:** Exactly one of `file` and `upload_ids` must be provided. Use
        `POST /doc-ai/v1/job/upload` to obtain upload IDs.


        **Processing:** the job runs asynchronously. Poll `GET
        /doc-ai/v1/job/{job_id}/status` until a terminal status (`completed`,
        `partially_completed`, `failed`, `rejected`), then fetch output via the
        results or download-url endpoints.


        Digitise JSON results include blocks with text, tag and bounding box.
      tags:
        - docAi
      parameters:
        - name: api-subscription-key
          in: header
          required: true
          schema:
            type: string
      responses:
        '201':
          description: Created
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocAIStartJobResponse'
        '400':
          description: Invalid request or schema
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocAIErrorModel'
        '402':
          description: Billing or entitlement error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocAIErrorModel'
        '403':
          description: Forbidden
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocAIErrorModel'
        '413':
          description: File too large
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocAIErrorModel'
        '429':
          description: Rate or admission limit exceeded
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocAIErrorModel'
        '503':
          description: Billing unavailable
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/DocAIErrorModel'
      requestBody:
        content:
          multipart/form-data:
            schema:
              type: object
              properties:
                file:
                  type: array
                  items:
                    type: string
                    format: binary
                  description: >-
                    Document file(s) to digitise. Repeatable multipart part.
                    Exactly one of `file` and `upload_ids` must be provided.
                upload_ids:
                  type: string
                  description: >-
                    Comma-separated upload IDs returned by `POST
                    /doc-ai/v1/job/upload`. Exactly one of `file` and
                    `upload_ids` must be provided.
                language:
                  type: string
                  default: en-IN
                  description: >-
                    Language code of the document (BCP-47), e.g. `en-IN`,
                    `hi-IN`.
                output_format:
                  $ref: >-
                    #/components/schemas/DocAiV1JobDigitisePostRequestBodyContentMultipartFormDataSchemaOutputFormat
                  default: html
                  description: Output format of the digitised document.
                content_type:
                  $ref: >-
                    #/components/schemas/DocAiV1JobDigitisePostRequestBodyContentMultipartFormDataSchemaContentType
                  default: printed
                  description: Nature of the document content.
                auto_orient:
                  type: string
                  default: 'true'
                  description: >-
                    Automatically correct page orientation before processing.
                    Boolean sent as text: `true` or `false`.
                model:
                  type: string
                  default: sarvam-vision-v1
                  description: Model to use for digitisation.
servers:
  - url: https://api.sarvam.ai
    description: Production
components:
  schemas:
    DocAiV1JobDigitisePostRequestBodyContentMultipartFormDataSchemaOutputFormat:
      type: string
      enum:
        - html
        - md
      default: html
      description: Output format of the digitised document.
      title: >-
        DocAiV1JobDigitisePostRequestBodyContentMultipartFormDataSchemaOutputFormat
    DocAiV1JobDigitisePostRequestBodyContentMultipartFormDataSchemaContentType:
      type: string
      enum:
        - printed
        - handwritten
        - mixed
      default: printed
      description: Nature of the document content.
      title: >-
        DocAiV1JobDigitisePostRequestBodyContentMultipartFormDataSchemaContentType
    DocAIStartJobResponse:
      type: object
      properties:
        job_id:
          type: string
          description: The unique identifier of the job.
        status:
          type: string
          description: Current status of the job.
        run_id:
          type: string
          description: The unique identifier of the job run.
      required:
        - job_id
        - status
        - run_id
      title: DocAIStartJobResponse
    DocAIErrorDetail:
      type: object
      properties:
        location:
          type: string
          description: >-
            Where the error occurred, e.g. 'body.items[3].tags' or
            'path.thing-id'.
        message:
          type: string
          description: Error message text.
        value:
          description: The value at the given location.
      title: DocAIErrorDetail
    DocAIErrorModel:
      type: object
      properties:
        type:
          type: string
          format: uri
          default: about:blank
          description: A URI reference to human-readable documentation for the error.
        title:
          type: string
          description: A short, human-readable summary of the problem type.
        status:
          type: integer
          description: HTTP status code.
        detail:
          type: string
          description: >-
            A human-readable explanation specific to this occurrence of the
            problem.
        instance:
          type: string
          format: uri
          description: >-
            A URI reference that identifies the specific occurrence of the
            problem.
        errors:
          type:
            - array
            - 'null'
          items:
            $ref: '#/components/schemas/DocAIErrorDetail'
          description: Optional list of individual error details.
      title: DocAIErrorModel
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: api-subscription-key

```

## Examples



**Request**

```json
{
  "file": []
}
```

**Response**

```json
{
  "job_id": "string",
  "status": "string",
  "run_id": "string"
}
```

**SDK Code**

```typescript
import { SarvamAIClient } from "sarvamai";

async function main() {
    const client = new SarvamAIClient({
        apiSubscriptionKey: "YOUR_API_KEY_HERE",
    });
    await client.docAi.digitise(, {});
}
main();

```

```python
from sarvamai import SarvamAI

client = SarvamAI(
    api_subscription_key="YOUR_API_KEY_HERE",
)

client.doc_ai.digitise(
    file=["example_file"],
)

```

```go
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.sarvam.ai/doc-ai/v1/job/digitise"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"auto_orient\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"content_type\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_format\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_ids\"\r\n\r\n\r\n-----011000010111000001101001--\r\n")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("api-subscription-key", "<apiSubscriptionKey>")
	req.Header.Add("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.sarvam.ai/doc-ai/v1/job/digitise")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["api-subscription-key"] = '<apiSubscriptionKey>'
request["Content-Type"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"auto_orient\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"content_type\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_format\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_ids\"\r\n\r\n\r\n-----011000010111000001101001--\r\n"

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.post("https://api.sarvam.ai/doc-ai/v1/job/digitise")
  .header("api-subscription-key", "<apiSubscriptionKey>")
  .header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"auto_orient\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"content_type\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_format\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_ids\"\r\n\r\n\r\n-----011000010111000001101001--\r\n")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.sarvam.ai/doc-ai/v1/job/digitise', [
  'headers' => [
    'Content-Type' => 'multipart/form-data; boundary=---011000010111000001101001',
    'api-subscription-key' => '<apiSubscriptionKey>',
  ],
]);

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://api.sarvam.ai/doc-ai/v1/job/digitise");
var request = new RestRequest(Method.POST);
request.AddHeader("api-subscription-key", "<apiSubscriptionKey>");
request.AddHeader("Content-Type", "multipart/form-data; boundary=---011000010111000001101001");
request.AddParameter("multipart/form-data; boundary=---011000010111000001101001", "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"auto_orient\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"content_type\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"language\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"model\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_format\"\r\n\r\n\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"upload_ids\"\r\n\r\n\r\n-----011000010111000001101001--\r\n", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = [
  "api-subscription-key": "<apiSubscriptionKey>",
  "Content-Type": "multipart/form-data; boundary=---011000010111000001101001"
]
let parameters = [
  [
    "name": "auto_orient",
    "value": 
  ],
  [
    "name": "content_type",
    "value": 
  ],
  [
    "name": "language",
    "value": 
  ],
  [
    "name": "model",
    "value": 
  ],
  [
    "name": "output_format",
    "value": 
  ],
  [
    "name": "upload_ids",
    "value": 
  ]
]

let boundary = "---011000010111000001101001"

var body = ""
var error: NSError? = nil
for param in parameters {
  let paramName = param["name"]!
  body += "--\(boundary)\r\n"
  body += "Content-Disposition:form-data; name=\"\(paramName)\""
  if let filename = param["fileName"] {
    let contentType = param["content-type"]!
    let fileContent = String(contentsOfFile: filename, encoding: String.Encoding.utf8)
    if (error != nil) {
      print(error as Any)
    }
    body += "; filename=\"\(filename)\"\r\n"
    body += "Content-Type: \(contentType)\r\n\r\n"
    body += fileContent
  } else if let paramValue = param["value"] {
    body += "\r\n\r\n\(paramValue)"
  }
}

let request = NSMutableURLRequest(url: NSURL(string: "https://api.sarvam.ai/doc-ai/v1/job/digitise")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "POST"
request.allHTTPHeaderFields = headers
request.httpBody = postData as Data

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```