sarvam-api

Integrate Sarvam AI APIs for multilingual chat, speech, translation, and document intelligence.

12|2|Updated Oct 2, 2025
One-click install
npx skills add https://github.com/hasanraiyan/resume --skill sarvam-api
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sarvam-api
Source: https://github.com/hasanraiyan/resume/tree/main/.agent/skills/sarvam-api
Command: npx skills add https://github.com/hasanraiyan/resume --skill sarvam-api

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you correctly integrate Sarvam AI’s Indian-language APIs so your agents can chat, transcribe, translate, synthesize speech, detect languages, and process documents without getting stuck on authentication, model quirks, or mismatched SDK methods.

Core Features & Use Cases

  • Chat LLM integration: Generate multilingual responses using the Sarvam chat completions endpoint with the correct headers and SDK call patterns.
  • Speech & language pipelines: Convert speech to text (with required mode for Saaras v3), translate speech to English text, synthesize speech from text, and handle transliteration and language detection.
  • Document intelligence: Run the Sarvam Vision batch pipeline to extract and retrieve results from documents via the required multi-step flow.

Quick Start

Ask an AI to generate a working example request for Sarvam chat completions using model sarvam-105b with Bearer authentication and return a response with correct handling for reasoning_effort-related fields.

Frequently Asked Questions about sarvam-api

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I integrate Sarvam AI APIs for Indian language text-to-speech and speech-to-text?

Integrating Sarvam AI APIs for Indian language speech-to-text and text-to-speech requires correct endpoint selection, Bearer authentication, and handling parameter constraints such as the required mode for Saaras v3.

What is the correct way to format language codes for Sarvam AI translation and transliteration endpoints?

Correct language code formatting for Sarvam AI translation and transliteration endpoints involves following specific parameter constraints to ensure reliable SDK and REST wiring without mismatched methods.

How do I run Sarvam Vision batch pipelines for document intelligence extraction?

To run Sarvam Vision batch pipelines for document intelligence extraction, you must execute a required multi-step flow to submit documents and retrieve the extracted results using the correct API endpoints.

Does Sarvam chat completions API support multilingual responses with custom reasoning effort fields?

Yes, the Sarvam chat completions API supports multilingual responses using models like sarvam-105b with Bearer authentication, requiring correct handling of reasoning_effort-related fields in the response.

Why does my Sarvam API integration return authentication error codes during chat completions?

Sarvam API integrations return authentication error codes during chat completions when required headers are missing or Bearer authentication is misconfigured, requiring correct SDK and REST wiring to resolve.