Your First Stream

Quick start

The example below opens an async streaming connection, collects all audio chunks, and writes them to a PCM file.

import asyncio
from shunyalabs import AsyncShunyaClient
from shunyalabs.tts import TTSConfig

async def main():
    async with AsyncShunyaClient() as client:
        config = TTSConfig(model="zero-indic", voice="Varun", response_format="pcm")
        chunks = []
        async for audio in await client.tts.stream("Hello!", config=config):
            chunks.append(audio)
        with open("output.pcm", "wb") as f:
            f.write(b"".join(chunks))

asyncio.run(main())

What happens under the hood

1. The SDK opens a WebSocket connection to wss://tts.shunyalabs.ai/ws/v1/audio/speech.
2. Your text and TTSConfig are sent as a JSON message.
3. The server begins streaming binary audio chunks as they are synthesized.
4. The async generator yields each chunk, allowing real-time playback or buffering.
5. When synthesis is complete, the server closes the stream.