Transcribe audio with speaker labels using AssemblyAI in Python

What you get

A Python script that transcribes an audio file and prints who said what, speaker by speaker.

Prerequisites

Python 3
An AssemblyAI API key

Steps

Install the SDK and set your key:

Shell

pip install assemblyai
export ASSEMBLYAI_API_KEY=<your-key>

Create transcribe.py:

Python

import os

from assemblyai import TranscriptStatus
from assemblyai.prerecorded.v2 import Transcriber, TranscriptionConfig

audio_file = "https://assembly.ai/wildfires.mp3"

config = TranscriptionConfig(
    language_detection=True,
    speaker_labels=True,
)

transcriber = Transcriber(api_key=os.environ["ASSEMBLYAI_API_KEY"])
transcript = transcriber.transcribe(audio_file, config=config)

if transcript.status == TranscriptStatus.error:
    raise RuntimeError(f"Transcription failed: {transcript.error}")

print(f"\nFull Transcript:\n\n{transcript.text}")

for utterance in transcript.utterances:
    print(f"Speaker {utterance.speaker}: {utterance.text}")

Test it

Run python transcribe.py. You should see the full transcript of the sample wildfires clip, then lines like Speaker A: ... and Speaker B: ....