> 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.

# How to set the sample rate (audio quality)

> Controls the audio quality and size of the generated output.

The `speech_sample_rate` parameter controls the audio quality and size of the generated output.

It is **optional**: if omitted, the default value is `24000 Hz` (premium quality).

### Supported values:

| Sample Rate (Hz) | Audio Quality Description              | Availability                |
| ---------------- | -------------------------------------- | --------------------------- |
| 8000             | Basic telephony quality                | All models & modes          |
| 16000            | Good quality voice                     | All models & modes          |
| 22050            | High-quality audio (default for v2)    | All models & modes          |
| 24000            | Premium audio quality (default for v3) | All models & modes          |
| 32000            | Broadcast quality                      | **bulbul:v3 REST API only** |
| 44100            | CD quality audio                       | **bulbul:v3 REST API only** |
| 48000            | Professional/Studio quality            | **bulbul:v3 REST API only** |

> **Note**
>
> **Important:** Sample rates above 24000 Hz (32000, 44100, 48000) are only available with **bulbul:v3** via the **REST API**. They are not supported in streaming mode.

### Example Code

#### Rest API

```python
from sarvamai import SarvamAI
from sarvamai.play import save

# Initialize the REST client
client = SarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")

# Generate speech using REST
audio = client.text_to_speech.convert(
    text="Welcome to Sarvam AI!",
    model="bulbul:v3",
    language_code="en-IN",
    speech_sample_rate=24000  # Set premium audio quality
)
save(audio, "output1.wav")

```

#### Streaming API

```python
import asyncio
import base64
from sarvamai import AsyncSarvamAI, AudioOutput
import websockets

async def tts_stream():
    client = AsyncSarvamAI(api_subscription_key="YOUR_SARVAM_API_KEY")

    async with client.text_to_speech_streaming.connect(model="bulbul:v3") as ws:
        await ws.configure(
            language_code="hi-IN", 
            speaker="shubh",
            speech_sample_rate=24000  # Set premium audio quality
        )
        print("Sent configuration")

        long_text = (
            "भारत की संस्कृति विश्व की सबसे प्राचीन और समृद्ध संस्कृतियों में से एक है।"
            "यह विविधता, सहिष्णुता और परंपराओं का अद्भुत संगम है, "
            "जिसमें विभिन्न धर्म, भाषाएं, त्योहार, संगीत, नृत्य, वास्तुकला और जीवनशैली शामिल हैं।"
        )

        await ws.convert(long_text)
        print("Sent text message")

        await ws.flush()
        print("Flushed buffer")

        chunk_count = 0
        with open("output.mp3", "wb") as f:
            async for message in ws:
                if isinstance(message, AudioOutput):
                    chunk_count += 1
                    audio_chunk = base64.b64decode(message.data.audio)
                    f.write(audio_chunk)
                    f.flush()

        print(f"All {chunk_count} chunks saved to output.mp3")
        print("Audio generation complete")

        
        if hasattr(ws, "_websocket") and not ws._websocket.closed:
            await ws._websocket.close()
            print("WebSocket connection closed.")


if __name__ == "__main__":
    asyncio.run(tts_stream())

# --- Notebook/Colab usage ---
# await tts_stream()

```

> Controls the audio quality and size of the generated output.