Welcome to Sarvam AI Documentation
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
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
Use the /speech-to-text endpoint to convert spoken language into written
text. Output is returned in the same input language. Know
more
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
Use the /text-to-speech endpoint to convert written text into spoken
words. Supports natural-sounding voices across 10 languages. Know
more
Use the /transliterate endpoint to convert text between different scripts
while maintaining the same language. Perfect for handling multiple writing
systems. Know
more
Use the /detect-language endpoint to automatically identify the language
of input text. Supports all major Indian languages with high accuracy.
Know
more
Getting Started
To get started with Sarvam APIs, follow these steps:
- Authenticate: Learn how to authenticate your API requests in the Authentication Guide.
- Meta Prompt: You can now use our Meta Prompt 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
- Try Examples: Use the Usage Guides to see examples and best practices.
Need Help?
If you have any questions or need assistance, visit our Help section or reach out to us on our Discord.