Skip to main content

Python package for AssemblyAI

Project description


Transcribe audio into text. Recognize made-up words and boost accuracy using custom language models.

Getting started

Run pip install and get an API token from

pip install -U assemblyai


import assemblyai

aai = assemblyai.Client(token='secret-token')

transcript = aai.transcribe('')

while transcript.status != 'completed':
    transcript = transcript.get()

text = transcript.text

Transcripts take about half the duration of the audio to complete.

Custom language models

The quickstart example transcribes audio using a generic English language model.

In order to retain accuracy with unique word sets, create a custom language model.

For this example, we create a model using a list of words/sentences found on a wikipedia page.

import assemblyai
import wikipedia

aai = assemblyai.Client(token='secret-token')

phrases ="Pokemon characters").content.split('\n')

model = aai.train(phrases)

transcript = aai.transcribe('', model=model)

while transcript.status != 'completed':
    transcript = transcript.get()

text = transcript.text

Model and Transcript attributes

Initially, models take six minutes to train, after which they can be invoked by ID.

model = aai.model(id=model_id)

Prior transcripts can also be called by ID.

transcript = aai.transcript(id=transcript_id)

To inspect additional attributes, like transcript.confidence try:


Or inspect the raw API responses using:


For additional background see:

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
assemblyai-0.1.6-py2.py3-none-any.whl (5.8 kB) Copy SHA256 hash SHA256 Wheel py2.py3
assemblyai-0.1.6.tar.gz (12.5 kB) Copy SHA256 hash SHA256 Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page