> Sarvam Voice Agents (Samvaad) is a voice AI agent platform for Indian languages: build, test and deploy AI calling agents on your own phone numbers, from ₹3 a minute. Start here: https://docs.sarvam.ai/voice-agents/why-voice-agents.
> For clean Markdown of any page, append `.md` to the page URL.
> For a complete documentation index, see https://docs.sarvam.ai/llms.txt. For a section index, append `/llms.txt` to any section URL (for example https://docs.sarvam.ai/voice-agents/llms.txt).
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server.

# AWS SageMaker

## Docs

- [Get started on SageMaker](https://docs.sarvam.ai/api/self-hosted/sagemaker/get-started.md): Prerequisites, IAM setup, AWS Marketplace subscription, and service quotas for deploying Sarvam models on Amazon SageMaker. Everything you need before your first endpoint.
- [Deploy Speech-to-Text (Saaras v3)](https://docs.sarvam.ai/api/self-hosted/sagemaker/deploy-saaras.md): Deploy the Saaras v3 speech-to-text model on Amazon SageMaker — real-time and streaming endpoints — from your AWS Marketplace subscription using boto3.
- [Deploy Sarvam Vision](https://docs.sarvam.ai/api/self-hosted/sagemaker/deploy-vision.md): Deploy the Sarvam Vision document-intelligence model on Amazon SageMaker — real-time, async, and batch — from your AWS Marketplace subscription. OCR and parse PDFs and images across 23 languages.
- [Deploy Text-to-Speech (Bulbul v3)](https://docs.sarvam.ai/api/self-hosted/sagemaker/deploy-bulbul.md): Deploy the Bulbul v3 text-to-speech model on Amazon SageMaker — real-time, server-side streaming (SSE), and bidirectional endpoints — from your AWS Marketplace subscription using boto3.
- [Deploy with Terraform](https://docs.sarvam.ai/api/self-hosted/sagemaker/terraform.md): Deploy a Sarvam SageMaker endpoint with Terraform. One apply provisions the IAM execution role, the model from your Marketplace package, the endpoint config, and a live endpoint.
- [API reference — Speech-to-Text](https://docs.sarvam.ai/api/self-hosted/sagemaker/api-saaras.md): The InvokeEndpoint request and response contract for a self-hosted Saaras v3 endpoint on SageMaker: parameters, the five output modes, response schema, the streaming protocol, and errors.
- [API reference — Sarvam Vision](https://docs.sarvam.ai/api/self-hosted/sagemaker/api-vision.md): The InvokeEndpoint request and response contract for a self-hosted Sarvam Vision endpoint on SageMaker: content types, custom-attribute options, limits, the JSON response envelope, and error codes.
- [API reference — Text-to-Speech](https://docs.sarvam.ai/api/self-hosted/sagemaker/api-bulbul.md): The InvokeEndpoint request and response contract for a self-hosted Bulbul v3 endpoint on SageMaker: parameters, the three inference modes (real-time, server-side streaming, bidirectional), voices, codecs, and errors.
- [Error handling on SageMaker](https://docs.sarvam.ai/api/self-hosted/sagemaker/errors.md): How every self-hosted Sarvam endpoint reports errors on SageMaker: the 424 collapse through InvokeEndpoint, the shared error envelope, and the overload back-off rule for Saaras v3, Bulbul v3, and Sarvam Vision.
- [Configure & tune](https://docs.sarvam.ai/api/self-hosted/sagemaker/configure.md): Tune a Sarvam SageMaker endpoint with container environment variables — concurrency, default output mode, and GPU behaviour — set at model-creation time.
- [Operations](https://docs.sarvam.ai/api/self-hosted/sagemaker/operations.md): Run Sarvam SageMaker endpoints in production: instance sizing and pricing, autoscaling and scale-to-zero, CloudWatch monitoring, security and data residency, and updating model versions.
- [Limitations](https://docs.sarvam.ai/api/self-hosted/sagemaker/limitations.md): Known constraints of Sarvam self-hosted SageMaker deployments: network isolation, payload and duration limits, page caps, and region-specific packages. Read before you build.
- [Troubleshooting](https://docs.sarvam.ai/api/self-hosted/sagemaker/troubleshooting.md): Fix common issues with Sarvam SageMaker deployments: failed model creation, endpoints stuck creating, invoke errors, latency and throttling. Diagnose with CloudWatch.