Skip to main content
Article·assemblyai.com
speech-to-textaudio-aitranscriptionspeaker-diarizationaudio-intelligence

AssemblyAI

Explore AssemblyAI, a speech AI API platform, to transcribe audio/video, detect speakers, analyze sentiment, and more. This action pack guides you through setting up AssemblyAI and performing a basic transcription.

beginner10 min3 steps
The play
  1. Sign up for AssemblyAI
    Go to AssemblyAI's website (https://www.assemblyai.com/) and sign up for a free account to get your API key.
  2. Install the AssemblyAI Python client
    Open your terminal and install the AssemblyAI Python client using pip.
  3. Transcribe a local audio file
    Create a Python script, replace 'YOUR_API_KEY' with your actual AssemblyAI API key, and 'path/to/your/audio.wav' with the path to your audio file. Run the script to transcribe the audio.
Starter code
import assemblyai as aai

aai.settings.api_key = "YOUR_API_KEY"

config = aai.TranscriptionConfig(language_code="en_US")

transcriber = aai.Transcriber(config=config)

transcript = transcriber.transcribe("path/to/your/audio.wav")

print(transcript.text)
Source
AssemblyAI — Action Pack