Voice Selection

Female Voices

Male Voices

Sarvam API Docs

Authentication

Credits & Rate Limits

Talk to us

Access to Beta APIs

API Change Log

API Examples & Usage

Meta Prompt Guide

Translates input text to the target language.

Translate Text

Given a PDF, this API helps to get structured extraction of data in the document.The API returns a base64 encoded XML string containing the extracted data.

Sarvam Parse

Given a PDF, this API helps to translate the content in the document

Doc Translate

This API transcribes speech to text in multiple Indian languages and English. It supports real-time transcription. It uses Saarika model for transcription.

**Real-Time API** (Current Endpoint): For quick responses under 30 seconds with immediate results

### Note:
- For longer audio files: Please follow Batch API notebook script - [View Notebook](https://github.com/sarvamai/sarvam-ai-cookbook/tree/main/notebooks/stt/stt-batch-api)
- Only Batch API supports diarization (speaker identification)
- Diarization is only available in Batch API with separate pricing
- Please refer to [dashboard.sarvam.ai](https://dashboard.sarvam.ai) for detailed pricing information

Real-Time Speech to Text API

This API automatically detects the input language, transcribes the speech, and translates the text to English.It uses Saaras model for translation.

*Real-Time API* (Current Endpoint): For quick responses under 30 seconds with immediate results.

### Note:
- For longer audio files: Please follow Batch API notebook script - [View Notebook](https://github.com/sarvamai/sarvam-ai-cookbook/blob/main/notebooks/stt-translate/STT_Translate_API_Tutorial.ipynb)
- Only Batch API supports diarization (speaker identification).
- Diarization is only available in Batch API with separate pricing.
- Please refer to [dashboard.sarvam.ai](https://dashboard.sarvam.ai) for detailed pricing information.

Real Time Speech To Text Translate API

Given an audio file of a call between two parties and a list of questions, this API analyzes the content and returns the transcript, along with responses to the questions. Each response is supported by reasoning and exact phrases extracted from the transcript.

Call Analytics

This endpoint performs comprehensive text analysis on provided content and answers specific questions about the text. Each response is supported by reasoning and the exact phrase extracted from the content.

Text Analytics

This is the model to convert text into spoken audio. 
The output is a wave file encoded as a base64 string.

Speaker	Accent	Value	Listen
Meera	Indian	`meera`	🎧 Listen
Pavithra	Indian	`pavithra`	🎧 Listen
Maitreyi	Indian	`maitreyi`	🎧 Listen
Diya	Indian	`diya`	🎧 Listen
Maya	Indian	`maya`	🎧 Listen
Misha	Western	`misha`	🎧 Listen

Speaker	Accent	Value	Listen
Arvind	Indian	`arvind`	🎧 Listen
Amol	Indian	`amol`	🎧 Listen
Amartya	Indian	`amartya`	🎧 Listen
Neel	Indian	`neel`	🎧 Listen
Arjun	Indian	`arjun`	🎧 Listen
Vian	Western	`vian`	🎧 Listen

Getting Started

Changelog

Usage Guides

Endpoints

Voice Selection

Voice Selection

Female Voices

Male Voices

Getting Started

Changelog

Usage Guides

Endpoints

​Voice Selection

​Female Voices

​Male Voices

Voice Selection

Female Voices

Male Voices