afizs / assembly-ai-plus

assembly-ai-plus

Simple Library for transcribing and understanding audio and video files using AssemblyAI.

Read more about AssemblyAI 👉 Docs

Install

pip install assembly-ai-plus

How it works

sequenceDiagram
  participant User
  User->>submit_audio_for_transcription: Audio URL or Local file path and include other intelligence features
  submit_audio_for_transcription-->>User: transcription_id
  User->>get_transcription_results: transcription_id, all_details=True/False
  get_transcription_results-->>User: Full Transcription Results

Loading

How to use

This Library provides a AssemblyAI class using which you can submit audio files for transcribing and understanding.

from assembly_ai_plus.assemblyai import AssemblyAI

First create the assembly_ai instance by providing the AssemblyAI API KEY, which you can get it for free from here

assembly_ai = AssemblyAI(api_key='YOURKEY')

Submit the audio url for transcription

res = assembly_ai.submit_audio_for_transcription(audio_url="https://bit.ly/3yxKEIY")

res.get('id') # This id is used to extract the actual text from the audio files.

'rsh0hzmusy-024f-472e-937b-e86223eaf7c9'

Sumbit Local Audio file for transcription

res = assembly_ai.submit_audio_for_transcription(local_audio_file_path='your_file_path')

res.get('id')

'rsh0n4g7nv-f022-409b-b97b-9a138261a0d7'

Getting the Transcription Result

full_details = assembly_ai.get_transcription_results('rs3c8julbq-177d-4071-ab6f-d7c7a9bb6dbb')

print(full_details['text'])

You know, demons on TV like that. And and for people to expose themselves to being rejected on TV or, you know, humili humiliated by Fear Factor or, you know.

We can check out other details like sentiment analysis from full_details