Language Identification API

Overview

The Language Identification (LID) API identifies the language (e.g., en-IN, hi-IN) and script (e.g., Latin, Devanagari) of the input text. It supports multiple Indian languages and scripts, making it ideal for multilingual text processing.

Detection Types

Single Language

Detect the primary language and script of text input. Example: “Hello, how are you?” → language: en-IN, script: Latn

Auto Detection

Automatic language detection for seamless integration with translation and preprocessing APIs.

Code Examples

1 from sarvamai import SarvamAI
2 
3 client = SarvamAI(
4     api_subscription_key="YOUR_SARVAM_API_KEY"
5 )
6 
7 response = client.text.identify_language(
8     input="Hello, how are you?"
9 )
10 
11 print(f"Request ID: {response.request_id}")
12 print(f"Language Code: {response.language_code}")  # Output: en-IN
13 print(f"Script Code: {response.script_code}")      # Output: Latn

Response Format

1 {
2   "request_id": "string | null",
3   "language_code": "string | null",
4   "script_code": "string | null"
5 }

Supported Languages and Scripts

Language Support

Available Languages:

en-IN: English
hi-IN: Hindi
bn-IN: Bengali
gu-IN: Gujarati
kn-IN: Kannada
ml-IN: Malayalam
mr-IN: Marathi
od-IN: Odia
pa-IN: Punjabi
ta-IN: Tamil
te-IN: Telugu

Script Support

Available Scripts:

Latn: Latin (Romanized script)
Deva: Devanagari (Hindi, Marathi)
Beng: Bengali
Gujr: Gujarati
Knda: Kannada
Mlym: Malayalam
Orya: Odia
Guru: Gurmukhi
Taml: Tamil
Telu: Telugu

API Response Format

Field	Type	Description
`request_id`	string	Unique identifier for the request
`language_code`	string	Detected language in BCP-47 format (e.g., `hi-IN`, `ta-IN`)
`script_code`	string	Detected script code (e.g., `Deva`, `Latn`, `Taml`)

Supported languages: en-IN, hi-IN, bn-IN, gu-IN, kn-IN, ml-IN, mr-IN, od-IN, pa-IN, ta-IN, te-IN

1 {
2   "request_id": "20241115_12345678-1234-5678-1234-567812345678",
3   "language_code": "hi-IN",
4   "script_code": "Deva"
5 }

Script Codes Reference

Script Code	Script Name	Used By
`Latn`	Latin	English
`Deva`	Devanagari	Hindi, Marathi
`Beng`	Bengali	Bengali
`Gujr`	Gujarati	Gujarati
`Knda`	Kannada	Kannada
`Mlym`	Malayalam	Malayalam
`Orya`	Odia	Odia
`Guru`	Gurmukhi	Punjabi
`Taml`	Tamil	Tamil
`Telu`	Telugu	Telugu

Error Responses

All errors return a JSON object with an error field (message, code, request_id). The full error-code table, retry guidance, and SDK exception reference live on the central Errors & Troubleshooting page.

Errors specific to this endpoint:

HTTP Status	Error Code	When This Happens	What To Do
`400`	`invalid_request_error`	Missing required `input` parameter	Include the `input` field with text to identify
`422`	`unprocessable_entity_error`	Text too long (max 1000 characters)	Split text into smaller chunks

Error Handling Code Example

1 from sarvamai import SarvamAI
2 from sarvamai.core.api_error import ApiError
3 
4 client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")
5 
6 try:
7     response = client.text.identify_language(
8         input="Hello, how are you?"
9     )
10     print(f"Language: {response.language_code}")
11     print(f"Script: {response.script_code}")
12 except ApiError as e:
13     if e.status_code == 400:
14         print(f"Bad request: {e.body}")
15     elif e.status_code == 403:
16         print("Invalid API key. Check your credentials.")
17     elif e.status_code == 422:
18         print(f"Invalid parameters: {e.body}")
19     elif e.status_code == 429:
20         print("Rate limit exceeded. Wait and retry.")
21     else:
22         print(f"Error {e.status_code}: {e.body}")

Check out our detailed API Reference to explore Language Identification and all available options.

For detailed pricing information and usage tiers, visit our pricing page.