UNPKG

sarvam-mcp

Version:

An MCP server exposing Sarvam AI tools and a documentation retriever.

251 lines (222 loc) 8.44 kB
--- title: Mayura description: >- Advanced multilingual translation model supporting Indian languages with customizable translation styles and script control --- ## Overview Mayura is our powerful translation model that converts text between English and Indian languages while preserving meaning and context. For example: 'मैं ऑफिस जा रहा हूँ' translates to 'I am going to the office' in English, maintaining the original meaning across different scripts and languages. ## Features <CardGroup cols={2}> <Card title="Language Support" icon="language"> Support for 11 languages including English and major Indian languages with auto-detection </Card> {" "} <Card title="Translation Modes" icon="wand-magic-sparkles"> Multiple translation styles: formal, modern-colloquial, classic-colloquial, and code-mixed </Card> {" "} <Card title="Script Control" icon="pen-nib"> Flexible output script options: Roman, native, and spoken forms </Card> <Card title="Smart Processing" icon="gears"> Advanced preprocessing and numeral format control </Card> </CardGroup> ### Key Capabilities <Tabs> <Tab title="Basic Usage"> Simple translation between languages with default settings. Perfect for getting started with the Mayura API. <Tabs> <Tab title="Python"> ```python from sarvamai import SarvamAI client = SarvamAI( api_subscription_key="YOUR_API_SUBSCRIPTION_KEY" ) response = client.translate( input="मैं ऑफिस जा रहा हूँ", source_language_code="hi-IN", target_language_code="en-IN" ) ``` </Tab> <Tab title="JavaScript"> ```javascript const { SarvamAI } = require('sarvamai'); const client = new SarvamAI({ apiSubscriptionKey: 'YOUR_API_SUBSCRIPTION_KEY' }); const response = await client.text.translate({ input: 'मैं ऑफिस जा रहा हूँ', sourceLanguageCode: 'hi-IN', targetLanguageCode: 'en-IN' }); ``` </Tab> <Tab title="cURL"> ```bash curl -X POST https://api.sarvam.ai/translate \ -H "api-subscription-key: YOUR_API_SUBSCRIPTION_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": "मैं ऑफिस जा रहा हूँ", "source_language_code": "hi-IN", "target_language_code": "en-IN" }' ``` </Tab> </Tabs> </Tab> <Tab title="Translation Modes"> Customize the translation style with different modes to match your needs - formal, colloquial, or code-mixed. <Tabs> <Tab title="Python"> ```python # Translation with style control response = client.translate( input="Your EMI of Rs. 3000 is pending", source_language_code="en-IN", target_language_code="hi-IN", mode="modern-colloquial", # Options: formal, modern-colloquial, classic-colloquial, code-mixed speaker_gender="Female" # For code-mixed translations ) ``` </Tab> <Tab title="JavaScript"> ```javascript // Translation with style control const response = await client.text.translate({ input: 'Your EMI of Rs. 3000 is pending', sourceLanguageCode: 'en-IN', targetLanguageCode: 'hi-IN', mode: 'modern-colloquial', // Options: formal, modern-colloquial, classic-colloquial, code-mixed speakerGender: 'Female' // For code-mixed translations }); ``` </Tab> <Tab title="cURL"> ```bash curl -X POST https://api.sarvam.ai/translate \ -H "api-subscription-key: YOUR_API_SUBSCRIPTION_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": "Your EMI of Rs. 3000 is pending", "source_language_code": "en-IN", "target_language_code": "hi-IN", "mode": "modern-colloquial", "speaker_gender": "Female" }' ``` </Tab> </Tabs> </Tab> <Tab title="Script Control"> Control the output script format with options for Roman, native, and spoken forms. <Tabs> <Tab title="Python"> ```python # With script and numeral control response = client.translate( input="Your EMI of Rs. 3000 is pending", source_language_code="en-IN", target_language_code="hi-IN", output_script="fully-native", # Options: roman, fully-native, spoken-form-in-native numerals_format="native" # Options: international, native ) ``` </Tab> <Tab title="JavaScript"> ```javascript // With script and numeral control const response = await client.text.translate({ input: 'Your EMI of Rs. 3000 is pending', sourceLanguageCode: 'en-IN', targetLanguageCode: 'hi-IN', outputScript: 'fully-native', // Options: roman, fully-native, spoken-form-in-native numeralsFormat: 'native' // Options: international, native }); ``` </Tab> <Tab title="cURL"> ```bash curl -X POST https://api.sarvam.ai/translate \ -H "api-subscription-key: YOUR_API_SUBSCRIPTION_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": "Your EMI of Rs. 3000 is pending", "source_language_code": "en-IN", "target_language_code": "hi-IN", "output_script": "fully-native", "numerals_format": "native" }' ``` </Tab> </Tabs> <Note> Output script options provide different text representations: - roman: "aapka Rs. 3000 ka EMI pending hai" - fully-native: "आपका रु. 3000 का ई.एम.ऐ. पेंडिंग है।" - spoken-form-in-native: "आपका थ्री थाउजेंड रूपीस का ईएमअइ पेंडिंग है।" </Note> </Tab> <Tab title="Advanced Options"> Enable preprocessing and customize language detection for better translation quality. <Tabs> <Tab title="Python"> ```python # With advanced options response = client.translate( input="Your text here", source_language_code="auto", # Automatic language detection target_language_code="hi-IN", enable_preprocessing=True # Enable smart preprocessing ) ``` </Tab> <Tab title="JavaScript"> ```javascript // With advanced options const response = await client.text.translate({ input: 'Your text here', sourceLanguageCode: 'auto', // Automatic language detection targetLanguageCode: 'hi-IN', enablePreprocessing: true // Enable smart preprocessing }); ``` </Tab> <Tab title="cURL"> ```bash curl -X POST https://api.sarvam.ai/translate \ -H "api-subscription-key: YOUR_API_SUBSCRIPTION_KEY" \ -H "Content-Type: application/json" \ -d '{ "input": "Your text here", "source_language_code": "auto", "target_language_code": "hi-IN", "enable_preprocessing": true }' ``` </Tab> </Tabs> </Tab> </Tabs> ### Language Support | Language | Code | Translation Direction | | --------- | ----- | --------------------- | | English | en-IN | Both | | Hindi | hi-IN | Both | | Bengali | bn-IN | Both | | Gujarati | gu-IN | Both | | Kannada | kn-IN | Both | | Malayalam | ml-IN | Both | | Marathi | mr-IN | Both | | Odia | od-IN | Both | | Punjabi | pa-IN | Both | | Tamil | ta-IN | Both | | Telugu | te-IN | Both | <Note> All Indian languages support bidirectional translation with English. The 'auto' option in source_language_code enables automatic language detection. </Note>