Skip to main content

​
Endpoint

POST https://api.samuraiapi.in/v1/audio/transcriptions

​
Parameters

ParameterTypeRequiredDescription
filefile✅Audio file (mp3, mp4, wav, m4a, webm, ogg)
modelstring✅whisper-1
languagestring—ISO-639-1 language code (e.g. "en", "ja")
promptstring—Context hint to improve accuracy
response_formatstring—json (default), text, srt, vtt
temperaturenumber—Sampling temperature 0–1

​
Code Examples

from openai import OpenAI

client = OpenAI(
    api_key="sk-samurai-YOUR_KEY",
    base_url="https://api.samuraiapi.in/v1"
)

with open("audio.mp3", "rb") as audio_file:
    transcript = client.audio.transcriptions.create(
        model="whisper-1",
        file=audio_file,
        language="en",
        response_format="text"
    )

print(transcript)

​
Subtitle Generation (SRT)

with open("video_audio.mp3", "rb") as f:
    srt = client.audio.transcriptions.create(
        model="whisper-1",
        file=f,
        response_format="srt"
    )

with open("subtitles.srt", "w") as f:
    f.write(srt)

​
Supported Languages

Whisper supports 99 languages including English, Spanish, French, German, Japanese, Chinese, Arabic, Hindi, Portuguese, and more.

​
Pricing

whisper-1: **0.003/minute∗∗(SamuraiAI500.003/minute** (Samurai AI 50% discount from 0.006)