> 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 full documentation content in one file, see https://docs.sarvam.ai/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.sarvam.ai/_mcp/server.

# Deploy Text-to-Speech (Bulbul v3)

> 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 **Bulbul v3** as a SageMaker endpoint in your own account. This guide covers a real-time endpoint end to end with `boto3`, then server-side streaming (SSE) and bidirectional for lower latency. The full, runnable notebook lives in [`sarvamai/amazon-sagemaker-examples`](https://github.com/sarvamai/amazon-sagemaker-examples/tree/main/text-to-speech/bulbul-v3).

> **Note**
>
> **Model identifier.** In API requests you pass **`model: bulbul:v3`** — it is the only accepted value (`bulbul:v3-beta` and v2 are rejected). See the [API reference](/api/self-hosted/sagemaker/api-bulbul).

> **Warning**
>
> Bulbul v3 self-hosted supports **real-time** (`InvokeEndpoint`), **server-side streaming (SSE)** (`InvokeEndpointWithResponseStream`), **bidirectional** (`InvokeEndpointWithBidirectionalStream`), and **batch transform**. Use SSE or bidirectional for long text or low-latency playback.

## Prerequisites

Complete [Get started on SageMaker](/api/self-hosted/sagemaker/get-started) first: subscribe to the Bulbul v3 listing, copy your **model package ARN** for your region, and have an **execution role ARN** ready. Read the endpoint's [API reference](/api/self-hosted/sagemaker/api-bulbul) carefully before you integrate — the request contract is enforced by the container.

## Recommended instance

Deploy on **`ml.g6e.xlarge`** (1× NVIDIA L40S). Scale concurrency by adding instances or raising `WEB_CONCURRENCY` — not by choosing a larger single-GPU instance (vCPU/RAM don't change throughput). See [Configure & tune](/api/self-hosted/sagemaker/configure) for the serve-ceiling knobs.

## 1. Create the endpoint

**`Create endpoint`**

```python Create endpoint
import base64, json, boto3

sm      = boto3.client("sagemaker")
runtime = boto3.client("sagemaker-runtime")

model_name        = "bulbul-v3"
role              = "arn:aws:iam::<account>:role/<your-sagemaker-execution-role>"
# Copy this from your Marketplace subscription, for your region:
model_package_arn = "<Bulbul v3 model-package ARN for your region>"

sm.create_model(
    ModelName=model_name,
    PrimaryContainer={"ModelPackageName": model_package_arn},
    ExecutionRoleArn=role,
    EnableNetworkIsolation=True,
)
sm.create_endpoint_config(
    EndpointConfigName=model_name,
    ProductionVariants=[{
        "VariantName": "AllTraffic",
        "ModelName": model_name,
        "InstanceType": "ml.g6e.xlarge",
        "InitialInstanceCount": 1,
    }],
)
sm.create_endpoint(EndpointName=model_name, EndpointConfigName=model_name)
sm.get_waiter("endpoint_in_service").wait(EndpointName=model_name)
```

## 2. Invoke it

**Real-time** — JSON in, base64 audio out:

**`Real-time`**

```python Real-time
payload = {
    "text": "Namaste! Welcome to Sarvam.",
    "model": "bulbul:v3",
    "speaker": "shubh",
    "language_code": "en-IN",
    "output_audio_codec": "wav",
    "speech_sample_rate": 24000,
}
r = runtime.invoke_endpoint(
    EndpointName=model_name,
    ContentType="application/json",
    Accept="application/json",
    Body=json.dumps(payload),
)
audio = base64.b64decode(json.loads(r["Body"].read())["audios"][0])
```

**Server-side streaming (SSE)** — note `"stream": True` in the body (the flag lives in the payload, not an API parameter):

**`Streaming (SSE)`**

```python Streaming (SSE)
r = runtime.invoke_endpoint_with_response_stream(
    EndpointName=model_name,
    ContentType="application/json",
    Body=json.dumps({**payload, "output_audio_codec": "mp3", "stream": True}),
)
chunks = [e["PayloadPart"]["Bytes"] for e in r["Body"] if e.get("PayloadPart")]
```

**Bidirectional** — see the repo notebook `text-to-speech/bulbul-v3/bulbul-v3-text-to-speech-Model.ipynb` for the full HTTP/2 SigV4 client (`aws-sdk-sagemaker-runtime-http2`), including the `config` → `text` → `flush` frame loop.

See the full request and response schema in the [Text-to-Speech API reference](/api/self-hosted/sagemaker/api-bulbul).

## Clean up

GPU endpoints bill by the hour. Delete resources you're not using:

**`Cleanup`**

```python Cleanup
sm.delete_endpoint(EndpointName=model_name)
sm.delete_endpoint_config(EndpointConfigName=model_name)
sm.delete_model(ModelName=model_name)
```

#### [Prefer infrastructure-as-code?](/api/self-hosted/sagemaker/terraform)

Deploy the same endpoint with Terraform — IAM role, model, endpoint config, and endpoint in one `apply`.

> 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.