Create Transcription

A direct audio download URL or a page URL from an officially supported site. Supported site links are automatically resolved using the Link API’s extraction logic, and the original URL is saved on the transcription. See Get supported sites for the current list. If extraction fails, the request returns the corresponding Link API error. Direct download URLs continue to work without extraction. Other streaming or preview links are not supported. Automatic extraction is available only for single transcriptions, not batch requests. Either audio_url or audio_file must be provided, but not both.

Base64 encoded audio file content. Either audio_url or audio_file must be provided, but not both.

Base64 Encoding Example

Python:

import base64
from soferai import SoferAI

# Initialize client
client = SoferAI(api_key="your_api_key_here")

# Read and encode audio file
with open("audio.mp3", "rb") as f:
    base64_audio = base64.b64encode(f.read()).decode('utf-8')

# Create transcription request
response = client.transcribe.create_transcription(
    audio_file=base64_audio,
    info={
        "model": "v1",
        "primary_language": "en",
        "hebrew_word_format": ["he"],
        "title": "My Shiur Transcription"
    }
)

print(f"Transcription ID: {response}")