Limits & Quotas

Concurrent Requests

Shunya TTS allows up to 16 concurrent requests per API key. Use a semaphore to stay within the limit when processing batches.

Concurrency Limit

LIMIT	VALUE
Max concurrent requests	`16` per API key

Semaphore Example

Use asyncio.Semaphore to cap in-flight requests:

python

import asyncio
from shunyalabs import AsyncShunyaClient, TTSConfig

client = AsyncShunyaClient(api_key="your-api-key")
sem = asyncio.Semaphore(16)

async def synthesize(text: str, config: TTSConfig):
    async with sem:
        return await client.tts.synthesize(text, config=config)

async def main():
    config = TTSConfig(model="zero-indic", voice="Nisha", response_format="mp3")
    texts = ["Sentence one.", "Sentence two.", "Sentence three.", "..."]

    results = await asyncio.gather(
        *[synthesize(t, config) for t in texts]
    )
    for i, result in enumerate(results):
        with open(f"output_{i}.mp3", "wb") as f:
            f.write(result.audio_data)

asyncio.run(main())

PreviousRate Limits Next Overview & Base URLs