Migration guide: Deepgram to AssemblyAI | AssemblyAI

This guide walks through the process of migrating from Deepgram 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 local file by Deepgram and AssemblyAI:

Deepgram

AssemblyAI

1 from deepgram import (
2      DeepgramClient,
3      PrerecordedOptions,
4      FileSource,
5 )
6 
7 API_KEY = "YOUR_DG_API_KEY"
8 
9 AUDIO_FILE = "./example.wav"
10 
11 def main():
12     try:
13         deepgram = DeepgramClient(API_KEY)
14 
15         with open(AUDIO_FILE, "rb") as file:
16             buffer_data = file.read()
17 
18             payload: FileSource = {
19                 "buffer": buffer_data,
20             }
21 
22             options = PrerecordedOptions(
23                 model="nova-2",
24                 smart_format=True,
25                 diarize=True
26             )
27 
28             response = deepgram.listen.prerecorded.v("1").transcribe_file(payload, options)
29 
30             print(response.to_json(indent=4))
31 
32     except Exception as e:
33         print(f"Exception: {e}")
34 
35 if name == "main":
36     main()

Below is a side-by-side comparison of a basic snippet to transcribe a publicly-accessible URL by Deepgram and AssemblyAI:

Deepgram

AssemblyAI

1 from deepgram import (
2     DeepgramClient,
3     PrerecordedOptions
4 )
5 
6 API_KEY = "YOUR_DG_API_KEY"
7 
8 AUDIO_URL = {
9     "url": "https://dpgr.am/spacewalk.wav"
10 }
11 
12 def main():
13     try:
14         deepgram = DeepgramClient(API_KEY)
15 
16         options = PrerecordedOptions(
17             model="nova-2",
18             smart_format=True,
19             diarize=True
20         )
21 
22         response = deepgram.listen.prerecorded.v("1").transcribe_url(AUDIO_URL, options)
23 
24         print(response.to_json(indent=4))
25 
26     except Exception as e:
27         print(f"Exception: {e}")
28 
29 if name == "main":
30     main()

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 and Best is the default speech model if none is specified
We have a cookbook for error handling common errors when using our API.

Installation

Deepgram

AssemblyAI

1 from deepgram import (
2     DeepgramClient,
3     PrerecordedOptions,
4     FileSource,
5 )
6 
7 API_KEY = "YOUR_DG_API_KEY"
8 deepgram = DeepgramClient(API_KEY)

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

Get your API key from your AssemblyAI dashboard
To follow this guide, install AssemblyAI’s Python SDK by typing this code into your terminal:
pip install assemblyai

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

Deepgram

AssemblyAI

1 # Local Files
2 AUDIO_FILE = "example.wav"
3 with open(AUDIO_FILE, "rb") as file:
4     buffer_data = file.read()
5 
6 payload: FileSource = {
7     "buffer": buffer_data,
8 }
9 
10 options = PrerecordedOptions(
11     smart_format=True,
12     summarize="v2",
13 )
14 
15 file_response = deepgram.listen.rest.v("1").transcribe_file(payload, options)
16 
17 json = file_response.to_json()
18 
19 #Public URLs
20 AUDIO_URL = {
21     "url": "https://static.deepgram.com/examples/Bueller-Life-moves-pretty-fast.wav"
22 }
23 
24 options = PrerecordedOptions(
25     smart_format=True,
26     summarize="v2"
27 )
28 
29 url_response = deepgram.listen.rest.v("1").transcribe_url(AUDIO_URL, options)
30 
31 json = url_response.to_json()

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)

Adding Features

Deepgram

AssemblyAI

1 options = PrerecordedOptions(
2    model="nova-2",
3    smart_format=True,
4    diarize=True,
5    detect_entities=True
6 )
7 
8 response = deepgram.listen.prerecorded.v("1").transcribe_url(AUDIO_URL, options)

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