sarvam-mcp
Version:
An MCP server exposing Sarvam AI tools and a documentation retriever.
59 lines (50 loc) • 2.92 kB
Markdown
---
title: Welcome to Sarvam AI Documentation
slug: api-reference-docs/introduction
---
Sarvam provides Models & APIs across the stack to help developers build powerful applications. Whether you're looking to translate text, convert speech to text, or combine speech recognition with translation, Sarvam has you covered.
## Key Features
<CardGroup cols={2}>
<Card title="Translate Text" icon="language">
Use the `/translate` endpoint to translate text from one language to
another. Supports 10 Indic languages along with English, achieving
best-in-class performance. **[Know
more](/api-reference-docs/text/translate)**
</Card>
<Card title="Speech to Text" icon="headphones">
Use the `/speech-to-text` endpoint to convert spoken language into written
text. Output is returned in the same input language. **[Know
more](/api-reference-docs/speech-to-text/transcribe)**
</Card>
<Card title="Speech to Text Translate" icon="language">
Use the `/speech-to-text-translate` endpoint to combine speech recognition
and translation, allowing you to convert spoken language directly into
translated text. **[Know
more](/api-reference-docs/speech-to-text/translate)**
</Card>
<Card title="Text to Speech" icon="text-size">
Use the `/text-to-speech` endpoint to convert written text into spoken
words. Supports natural-sounding voices across 10 languages. **[Know
more](/api-reference-docs/text-to-speech/convert)**
</Card>
<Card title="Transliterate" icon="font">
Use the `/transliterate` endpoint to convert text between different scripts
while maintaining the same language. Perfect for handling multiple writing
systems. **[Know
more](/api-reference-docs/text/transliterate)**
</Card>
<Card title="Language Identification" icon="magnifying-glass">
Use the `/detect-language` endpoint to automatically identify the language
of input text. Supports all major Indian languages with high accuracy.
**[Know
more](/api-reference-docs/text/identify-language)**
</Card>
</CardGroup>
## Getting Started
To get started with Sarvam APIs, follow these steps:
1. **Authenticate**: Learn how to authenticate your API requests in the [Authentication Guide](/api-reference-docs/authentication).
2. **Meta Prompt**: You can now use our [Meta Prompt](/api-reference-docs/metaprompt) directly to guide any AI chat model with the context needed to use Sarvam's APIs effectively.
An example on AI Studio with Gemini's latest model: [Explore here](https://aistudio.google.com/app/prompts/14NyNJ8V4icyNPoRBm2UiFbhXxS9ooy0m)
3. **Try Examples**: Use the [Usage Guides](/api-reference-docs/combined_usage_guide) to see examples and best practices.
## Need Help?
If you have any questions or need assistance, visit our [Help](/api-reference-docs/help) section or reach out to us on our [Discord](https://discord.gg/5rAsykttcs).