Limits & Quotas

Concurrent Request Limits

Use asyncio.gather to run multiple batch transcriptions in parallel while staying within limits.

Using asyncio.gather

python

import asyncio
from shunyalabs import AsyncShunyaClient
from shunyalabs.asr import TranscriptionConfig

async def transcribe_many(files: list[str]):
    async with AsyncShunyaClient() as client:
        config = TranscriptionConfig(model="zero-indic")
        tasks = [client.asr.transcribe(f, config=config) for f in files]
        results = await asyncio.gather(*tasks, return_exceptions=True)
        return results

PreviousRate Limits Next Migrating from OpenAI Whisper