Migration guide: AWS Transcribe to AssemblyAI

This guide walks through the process of migrating from AWS Transcribe to AssemblyAI for transcribing pre-recorded audio.

Get Started

Before we begin, make sure you have an AssemblyAI account and an API key. You can sign up for a free account and get your API key from your dashboard.

Side-by-side code comparison

Below is a side-by-side comparison of a basic snippet to transcribe a file by AWS Transcribe and AssemblyAI:

AWS Transcribe

AssemblyAI

1 import time
2 import boto3
3 
4 def transcribe_file(job_name, file_uri, transcribe_client):
5     transcribe_client.start_transcription_job(
6         TranscriptionJobName=job_name,
7         Media={"MediaFileUri": file_uri},
8         MediaFormat="wav",
9         LanguageCode="en-US",
10     )
11 
12     max_tries = 60
13     while max_tries > 0:
14         max_tries -= 1
15 
16         job = transcribe_client.get_transcription_job(
17             TranscriptionJobName=job_name
18         )
19 
20         job_status = job["TranscriptionJob"]["TranscriptionJobStatus"]
21 
22         if job_status in ["COMPLETED", "FAILED"]:
23             print(f"Job {job_name} is {job_status}.")
24 
25         if job_status == "COMPLETED":
26             print(
27                 f"Download the transcript from\n"
28                 f"\t{job['TranscriptionJob']['Transcript']['TranscriptFileUri']}."
29             )
30             break
31         else:
32             print(f"Waiting for {job_name}. Current status is {job_status}.")
33             time.sleep(10)
34 
35 def main():
36     transcribe_client = boto3.client("transcribe")
37     file_uri = "s3://test-transcribe/answer2.wav"
38     transcribe_file("Example-job", file_uri, transcribe_client)
39 
40 if name == "main":
41     main()

Installation

AWS Transcribe

AssemblyAI

1 import boto3
2 import time
3 
4 transcribe_client = boto3.client("transcribe")

When migrating from AWS to AssemblyAI, you’ll first need to handle authentication and SDK setup:

Get your API key from your AssemblyAI dashboard

Things to know:

Store your API key securely in an environment variable
API key authentication works the same across all AssemblyAI SDKs

Audio File Sources

AWS Transcribe

AssemblyAI

1 def transcribe_file(job_name, file_uri, transcribe_client):
2     transcribe_client.start_transcription_job(
3         TranscriptionJobName=job_name,
4         Media={"MediaFileUri": file_uri},
5         MediaFormat="wav",
6         LanguageCode="en-US",
7     )

Here are helpful things to know when migrating your audio input handling:

There’s no need to specify the audio format to AssemblyAI - it’s auto-detected. AssemblyAI accepts almost every audio/video file type: here is a full list of all our supported file types
Our SDK handles file upload and transcription automatically in one step
For S3 files, you’ll need to generate pre-signed URLs (see example in cookbook)

Basic Transcription

AWS Transcribe

AssemblyAI

1 while max_tries > 0:
2     max_tries -= 1
3     job = transcribe_client.get_transcription_job(
4         TranscriptionJobName=job_name
5     )
6     job_status = job["TranscriptionJob"]["TranscriptionJobStatus"]
7     if job_status in ["COMPLETED", "FAILED"]:
8         break
9     time.sleep(10)

Here are helpful things to know about our transcribe method:

The SDK handles polling under the hood
Transcript is directly accessible via transcript.text
English is the default language. We recommend specifying speech_models=["universal-3-pro", "universal-2"] for the highest accuracy
We have a cookbook for error handling common errors when using our API.

Adding Features

AWS Transcribe

AssemblyAI

1 transcribe_client.start_transcription_job(
2     TranscriptionJobName=job_name,
3     Media={"MediaFileUri": file_uri},
4     Settings={
5         "ShowSpeakerLabels": True,
6         "MaxSpeakerLabels": 2
7     }
8 )

Key differences:

Use aai.TranscriptionConfig to specify any extra features that you wish to use
The results for Speaker Diarization are stored in transcript.utterances. To see the full transcript response object, refer to our API Reference.
Check our documentation for our full list of available features and their parameters

1	import time
2	import boto3
3
4	def transcribe_file(job_name, file_uri, transcribe_client):
5	transcribe_client.start_transcription_job(
6	TranscriptionJobName=job_name,
7	Media={"MediaFileUri": file_uri},
8	MediaFormat="wav",
9	LanguageCode="en-US",
10	)
11
12	max_tries = 60
13	while max_tries > 0:
14	max_tries -= 1
15
16	job = transcribe_client.get_transcription_job(
17	TranscriptionJobName=job_name
18	)
19
20	job_status = job["TranscriptionJob"]["TranscriptionJobStatus"]
21
22	if job_status in ["COMPLETED", "FAILED"]:
23	print(f"Job {job_name} is {job_status}.")
24
25	if job_status == "COMPLETED":
26	print(
27	f"Download the transcript from\n"
28	f"\t{job['TranscriptionJob']['Transcript']['TranscriptFileUri']}."
29	)
30	break
31	else:
32	print(f"Waiting for {job_name}. Current status is {job_status}.")
33	time.sleep(10)
34
35	def main():
36	transcribe_client = boto3.client("transcribe")
37	file_uri = "s3://test-transcribe/answer2.wav"
38	transcribe_file("Example-job", file_uri, transcribe_client)
39
40	if name == "main":
41	main()