Migrating

Migrating from OpenAI Whisper

Side-by-side code comparison, parameter mapping, and output format differences.

Installation

Before — OpenAI Whisper
pip install openai
After — Shunyalabs
pip install shunyalabs[ASR]

Basic transcription

Before — Whisper
from openai import OpenAI
client = OpenAI()
with open("audio.wav","rb") as f:
  r = client.audio 
    .transcriptions
    .create(model="whisper-1", file=f)
print(r.text)
After — Shunyalabs
from shunyalabs import AsyncShunyaClient
from shunyalabs.asr import TranscriptionConfig
async with AsyncShunyaClient() as client:
  r = await client.asr.transcribe(
    "audio.wav",
    config=TranscriptionConfig(
      model="zero-indic"))
print(r.text)

Parameter mapping

Whisper ParameterShunyalabs EquivalentNotes
model="whisper-1"model="zero-indic"Only available model.
language="en"language_code="en"Same ISO 639-1 codes.
temperature=0— not availableNot configurable.
prompt="..."enable_keyterm_normalizationUse for domain term boosting.
PreviousConcurrent Request LimitsNext From Google Cloud STT