Overview
Sarvam AI's APIs offer developers and enterprises seamless access to cutting-edge Indian language AI capabilities, built ground-up for Bharat-scale applications. From large language model (LLM) access to Speech-to-Text (STT), Text-to-Speech (TTS), translation, transliteration, language identification (LID), text analytics, call analytics, and document parsing & translation, these APIs are the foundation blocks for any multilingual, multimodal application. Optimized for scale and performance, Sarvam AI's APIs enable effortless integration into web, mobile, and voice-based platforms. Whether you are building intelligent chatbots, multilingual transcription systems, real-time translation engines, or audio analytics tools, the APIs are engineered to handle complex language nuances spanning 11+ Indian languages with support for native accents, regional scripts, and contextual understanding. Designed for developers and data teams alike, these APIs are production-ready out of the box with low latency, flexible pricing, and extensive documentation. As Sarvam AI continues to roll out newer models and capabilities, the API suite will grow to include an even wider range of state-of-the-art AI functions, making it easy to stay future-ready with just a few lines of code. Whether you are scaling conversational platforms, analyzing multilingual documents, or building audio-first interfaces, Sarvam AI's API platform is your gateway to India-centric, high-performance AI solutions.
Highlights
- Sarvam AI's APIs are a modular set of AI tools built for developers creating scalable AI applications tailored to Indian languages
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Description | Cost/month | Overage cost |
|---|---|---|---|
Speech to Text Websocket (Saaras V3) | Transform audio into text in real-time with our WebSocket-based streaming API. Built for applications requiring immediate speech processing with minimal delay. Charged at Rs. 30/hr (Billed per second of audio transcribed) | $5,000.00 | |
Speech to Text REST (Saaras V3) | Process short audio files with immediate response. Best for quick transcriptions and testing with a maximum duration of 30 seconds. Charged at Rs. 30/hr (Billed per second of audio transcribed) | $5,000.00 | |
Speech to Text Batch (Saaras V3) | Process long audio files (up to 2 hours) using synchronous or asynchronous methods. Ideal for meetings, interviews, call center recordings, and large-scale content processing pipelines. Charged at Rs. 30/hr (Billed per second of audio transcribed) | $5,000.00 | |
Speech to Text Diarization (Saaras V3) | Process long audio files (up to 2 hours) using synchronous or asynchronous methods with speaker identification. Ideal for meetings, interviews, call center recordings, and large-scale content processing pipelines. Charged at Rs. 45/hr (Billed per second of audio transcribed) | $5,000.00 | |
Text to Speech Websocket (Bubul V3) | WebSocket-based streaming endpoint that sends audio chunks progressively as text is processed. Connect once, stream text in, receive audio out - no polling, no repeated HTTP calls. Charged at Rs. 30/10k characters (Billed per character of input text) | $5,000.00 | |
Text to Speech Stream (Bubul V3) | Send text in, get a binary audio stream back. The response starts arriving as soon as the first audio chunk is ready, so you can begin playback or piping without waiting for the full file. No WebSocket handshake, no config messages, no connection lifecycle. One HTTP request, one streamed response. Charged at Rs. 30/10k characters (Billed per character of input text) | $5,000.00 | |
Text to Speech REST (Bulbul V3) | Provides a synchronous REST endpoint where a POST request with text returns base64-encoded audio as response. Charged at Rs. 30/10k characters (Billed per character of input text) | $5,000.00 | |
Text Translate (Mayura V1) | Mayura is our state-of-the-art text processing model that excels in handling Indian languages with features like translation, transliteration, and script conversion. Charged at Rs. 20/10k characters (Billed per character of input text) | $5,000.00 | |
Doc Digitization API | Sarvam Document Digitization API provides enterprise-grade document processing powered by Sarvam Vision, our state-of-the-art multimodal model. Transform any document into structured, searchable, and machine-readable data with world-class accuracy. Charged at Rs. 0.5 / page processed | $5,000.00 |
Vendor refund policy
No refund supported at the moment.
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
Software as a Service (SaaS)
SaaS delivers cloud-based software applications directly to customers over the internet. You can access these applications through a subscription model. You will pay recurring monthly usage fees through your AWS bill, while AWS handles deployment and infrastructure management, ensuring scalability, reliability, and seamless integration with other AWS services.
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.