> 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.

# Create

POST https://api.sarvam.ai/text-to-speech/pronunciation-dictionary
Content-Type: multipart/form-data

Upload a `.json` file to create a new pronunciation dictionary. Only supported by **bulbul:v3**.

The file should contain a JSON object with a `pronunciations` key mapping language codes to word-pronunciation pairs. See the [Pronunciation Dictionary guide](/api-reference-docs/api-guides-tutorials/text-to-speech/pronunciation-dictionary) for format details and examples.

The returned `dictionary_id` can be passed as `dict_id` in text-to-speech requests (REST, HTTP Stream, and WebSocket).

**Limits:** Max 10 dictionaries per user, 100 words per dictionary, 1 MB file size.

Reference: https://docs.sarvam.ai/api-reference/pronunciation-dictionary/create

## Authentication

- `api-subscription-key` header (required) — API Key authentication via header

## Request

### Body (multipart/form-data)

This endpoint expects a multipart form containing a file.

- `file` (file, required)

## Response

### 200

Successful Response

- `dictionary_id` (string, required) — Unique identifier for the created dictionary (e.g. `p_5cb7faa6`). Use this as the `dict_id` parameter in text-to-speech requests.

## Errors

### 400 Bad Request Error

Bad Request — Invalid JSON, missing required fields, or bad schema.

- `error` (Sarvam_Model_API_ErrorDetails, required) — Error details

### 403 Forbidden Error

Forbidden

- `error` (Sarvam_Model_API_ErrorDetails, required) — Error details

### 413 Content Too Large Error

Payload Too Large — File size exceeds the 1 MB limit.

- `error` (Sarvam_Model_API_ErrorDetails, required) — Error details

### 422 Unprocessable Entity Error

Unprocessable Entity — Word limit exceeded (>100 words per dictionary) or dictionary limit exceeded (>10 dictionaries per user).

- `error` (Sarvam_Model_API_ErrorDetails, required) — Error details

### 429 Too Many Requests Error

Quota Exceeded

- `error` (Sarvam_Model_API_ErrorDetails, required) — Error details

### 500 Internal Server Error

Internal Server Error

- `error` (Sarvam_Model_API_ErrorDetails, required) — Error details

## Types

### Sarvam_Model_API_ErrorDetails

- `request_id` (string, required, nullable)
- `message` (string, required) — Message describing the error
- `code` (enum, required) — Error code for the specific error that has occurred. Refer to the error code documentation for more details.
  - Allowed values: `invalid_request_error`, `internal_server_error`, `unprocessable_entity_error`, `insufficient_quota_error`, `invalid_api_key_error`, `authentication_error`, `not_found_error`, `rate_limit_exceeded_error`, `model_call_error`, `gateway_timeout_error`, `billing_service_unavailable_error`

## Examples

**Request**

```json
{
  "file": "<file: string>"
}
```

**Response**

```json
{
  "dictionary_id": "p_5cb7faa6"
}
```

**SDK Code**

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

const client = new SarvamAIClient({
  apiSubscriptionKey: process.env.SARVAM_API_KEY,
});

const response = await client.pronunciationDictionary.create({
  file: fs.createReadStream("pronunciations.json"),
});

```

```swift pronunciationDictionary_create_example
import Foundation

let url = URL(string: "https://api.sarvam.ai/text-to-speech/pronunciation-dictionary")!
let boundary = "Boundary-\(UUID().uuidString)"

var request = URLRequest(url: url)
request.httpMethod = "POST"
request.setValue("YOUR_SARVAM_API_KEY", forHTTPHeaderField: "api-subscription-key")
request.setValue("multipart/form-data; boundary=\(boundary)", forHTTPHeaderField: "Content-Type")

// Upload the pronunciation JSON as a file (not as a raw string).
let fileURL = URL(fileURLWithPath: "pronunciations.json")
let fileData = try Data(contentsOf: fileURL)

var body = Data()
body.append("--\(boundary)\r\n".data(using: .utf8)!)
body.append("Content-Disposition: form-data; name=\"file\"; filename=\"pronunciations.json\"\r\n".data(using: .utf8)!)
body.append("Content-Type: application/json\r\n\r\n".data(using: .utf8)!)
body.append(fileData)
body.append("\r\n".data(using: .utf8)!)
body.append("--\(boundary)--\r\n".data(using: .utf8)!)

request.httpBody = body

let task = URLSession.shared.dataTask(with: request) { data, response, error in
    if let error = error {
        print("Error:", error)
        return
    }
    if let data = data, let json = String(data: data, encoding: .utf8) {
        print(json)
    }
}
task.resume()

```

```python pronunciationDictionary_create_example
import requests

url = "https://api.sarvam.ai/text-to-speech/pronunciation-dictionary"

files = { "file": "open('string', 'rb')" }
headers = {"api-subscription-key": "<apiSubscriptionKey>"}

response = requests.post(url, files=files, headers=headers)

print(response.json())
```

```go pronunciationDictionary_create_example
package main

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

func main() {

	url := "https://api.sarvam.ai/text-to-speech/pronunciation-dictionary"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"string\"\r\nContent-Type: application/octet-stream\r\n\r\n\r\n-----011000010111000001101001--\r\n")

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

	req.Header.Add("api-subscription-key", "<apiSubscriptionKey>")

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

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

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

}
```

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

url = URI("https://api.sarvam.ai/text-to-speech/pronunciation-dictionary")

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

request = Net::HTTP::Post.new(url)
request["api-subscription-key"] = '<apiSubscriptionKey>'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"string\"\r\nContent-Type: application/octet-stream\r\n\r\n\r\n-----011000010111000001101001--\r\n"

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

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

HttpResponse<String> response = Unirest.post("https://api.sarvam.ai/text-to-speech/pronunciation-dictionary")
  .header("api-subscription-key", "<apiSubscriptionKey>")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"string\"\r\nContent-Type: application/octet-stream\r\n\r\n\r\n-----011000010111000001101001--\r\n")
  .asString();
```

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

$client = new \GuzzleHttp\Client();

$response = $client->request('POST', 'https://api.sarvam.ai/text-to-speech/pronunciation-dictionary', [
  'multipart' => [
    [
        'name' => 'file',
        'filename' => 'string',
        'contents' => null
    ]
  ]
  'headers' => [
    'api-subscription-key' => '<apiSubscriptionKey>',
  ],
]);

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

```csharp pronunciationDictionary_create_example
using RestSharp;

var client = new RestClient("https://api.sarvam.ai/text-to-speech/pronunciation-dictionary");
var request = new RestRequest(Method.POST);
request.AddHeader("api-subscription-key", "<apiSubscriptionKey>");
request.AddParameter("undefined", "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"string\"\r\nContent-Type: application/octet-stream\r\n\r\n\r\n-----011000010111000001101001--\r\n", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);
```