Please confirm you are human

This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.

A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.

Hold with a pointer, or hold Space or Enter.

News

@SarvamAI
docs.sarvam.ai > api > api-guides-tutorials > speech-to-text > realtime-api

Realtime Speech-to-Text API - saaras:v3-realtime by Sarvam AI

4+ hour, 27+ min ago   (481+ words) Realtime Speech-to-Text API Sarvam API Docs Speech, text & chat model APIs - How this differs from the legacy Streaming API saaras:v3-realtime is Sarvam’s WebSocket streaming model for voice agents and live transcription: real interim (partial) transcripts as the user speaks,…...

Sarvam API Docs
docs.sarvam.ai > api > api-guides-tutorials > dubbing > how-to > specify-language-codes

How to specify language codes

5+ day, 6+ hour ago   (133+ words) Sarvam API Docs Speech, text & chat model APIs Dubbing uses BCP-47 codes for both the source language (spoken in your file) and the target languages you want back. In the REST body those fields are src_lang / target_langs; in the Python SDK they…...

@SarvamAI
docs.sarvam.ai > api > api-guides-tutorials > dubbing > overview

Dubbing API Overview - Video & Audio Localization by Sarvam AI

5+ day, 6+ hour ago   (534+ words) Speech, text & chat model APIs The Dubbing API takes a source video or audio file and returns a fully localized version in one or more Indian languages, transcribed, translated, re-voiced, and re-mixed back onto the original timeline. Optionally, it clones…...

@SarvamAI
docs.sarvam.ai > api > integration > langchain

Build with Sarvam AI in LangChain

1+ week, 4+ day ago   (315+ words) Speech, text & chat model APIs LangChain is a Python framework for building LLM applications, giving you a single set of interfaces (invoke, stream, bind_tools, with_structured_output, and more) that work the same way across different model providers. Instead of learning each provider’s own…...

Sarvam API Docs
docs.sarvam.ai > api > developer-tools > agent-skills

Agent Skills

1+ week, 4+ day ago   (98+ words) Speech, text & chat model APIs An assistant’s training data goes stale, and Sarvam’s SDK has a few patterns that don’t match what a model expects from an OpenAI-shaped client: Each skill is a short SKILL.md covering only these corrections,…...

Sarvam AI Docs
docs.sarvam.ai > docai > getting-started > overview

Welcome to Sarvam Doc AI | Sarvam API Docs

2+ week, 5+ day ago   (868+ words) Extract & digitise documents Extract and digitise any document in Hindi, Bengali, Tamil, Telugu, English, and 18 more Indian languages. No code required. Under the hood, Sarvam Vision powers all extraction and digitisation: a 3B-parameter document-intelligence model with SOTA accuracy on 22 Indian…...

@SarvamAI
docs.sarvam.ai > api-reference-docs > api-guides-tutorials > text-to-speech > voices

Voices - Sarvam AI Text-to-Speech Samples

3+ week, 4+ day ago   (163+ words) Want to test your own text? Head to dashboard.sarvam.ai to generate live previews with custom input. Not sure which voice to pick? Best Practices: Speaker Selection ranks every voice by measured pronunciation accuracy (CER) and recommends the best…...

Sarvam AI Docs
docs.sarvam.ai > api-reference-docs > errors-troubleshooting

Errors & Troubleshooting | Sarvam API Docs

2+ mon, 2+ day ago   (265+ words) Errors & Troubleshooting Sarvam AI Docs Use this page when a request fails or behaves unexpectedly. Endpoint reference pages document per-field validation; this page explains what failed, how to fix it, and how to retry safely. Most REST errors return JSON:…...

Google News
docs.sarvam.ai > api-reference-docs > developer-tools > mcp

MCP Server | Sarvam API Docs

2+ mon, 2+ day ago   (159+ words) The Sarvam docs expose a Model Context Protocol (MCP) server. Connect it to your AI coding assistant and the assistant can search the live documentation on demand — so the code it writes uses the right models, parameters, and endpoints instead…...