Topic Detection

Supported languages

Global Englishen

Australian Englishen_au

British Englishen_uk

US Englishen_us

Spanishes

Frenchfr

Germande

Italianit

Portuguesept

Supported models

Universal-3 Prouniversal-3-pro

Universal-2universal-2

Supported regions

US & EU

The Topic Detection model lets you identify different topics in the transcript. The model uses the IAB Content Taxonomy, a standardized language for content description which consists of 698 comprehensive topics.

Quickstart

Python

Python SDK

JavaScript

JavaScript SDK

Enable Topic Detection by setting iab_categories to true in the JSON payload.

1 import requests
2 import time
3 
4 base_url = "https://api.assemblyai.com"
5 
6 headers = {
7     "authorization": "<YOUR_API_KEY>"
8 }
9 
10 with open("./local_file.mp3", "rb") as f:
11     response = requests.post(base_url + "/v2/upload",
12                             headers=headers,
13                             data=f)
14 
15 upload_url = response.json()["upload_url"]
16 
17 data = {
18     "audio_url": upload_url, # You can also use a URL to an audio or video file on the web
19     "speech_models": ["universal-3-pro", "universal-2"],
20     "language_detection": True,
21     "iab_categories": True
22 }
23 
24 url = base_url + "/v2/transcript"
25 response = requests.post(url, json=data, headers=headers)
26 
27 transcript_id = response.json()['id']
28 polling_endpoint = base_url + "/v2/transcript/" + transcript_id
29 
30 print(f"Transcript ID: {transcript_id}")
31 
32 while True:
33     transcription_result = requests.get(polling_endpoint, headers=headers).json()
34 
35     if transcription_result['status'] == 'completed':
36       # Get the parts of the transcript that were tagged with topics
37       for result in transcription_result['iab_categories_result']['results']:
38         print(result['text'])
39         print(f"Timestamp: {result['timestamp']['start']} - {result['timestamp']['end']}")
40 
41         for label in result['labels']:
42           print(f"{label['label']} ({label['relevance']})")
43 
44       # Get a summary of all topics in the transcript
45       for topic, relevance in transcription_result['iab_categories_result']['summary'].items():
46         print(f"Audio is {relevance * 100}% relevant to {topic}")
47       break
48     elif transcription_result['status'] == 'error':
49         raise RuntimeError(f"Transcription failed: {transcription_result['error']}")
50     else:
51         time.sleep(3)

Example output

1 Smoke from hundreds of wildfires in Canada is triggering air quality alerts throughout the US. Skylines...
2 Timestamp: 250 - 28920
3 Home&Garden>IndoorEnvironmentalQuality (0.9881)
4 NewsAndPolitics>Weather (0.5561)
5 MedicalHealth>DiseasesAndConditions>LungAndRespiratoryHealth (0.0042)
6 ...
7 Audio is 100.0% relevant to NewsAndPolitics>Weather
8 Audio is 93.78% relevant to Home&Garden>IndoorEnvironmentalQuality
9 ...

Topic Detection Using LLM Gateway

Check out this cookbook Custom Topic Tags for an example of how to use LLM Gateway to create custom topic tags.

API reference

Request

$ curl https://api.assemblyai.com/v2/transcript \
> --header "Authorization: <YOUR_API_KEY>" \
> --header "Content-Type: application/json" \
> --data '{
>   "audio_url": "YOUR_AUDIO_URL",
>   "iab_categories": true
> }'

Key	Type	Description
`iab_categories`	boolean	Enable Topic Detection.

Response

Key	Type	Description
`iab_categories_result`	object	The result of the Topic Detection model.
`iab_categories_result.status`	string	Is either `success`, or `unavailable` in the rare case that the Topic Detection model failed.
`iab_categories_result.results`	array	An array of the Topic Detection results.
`iab_categories_result.results[i].text`	string	The text in the transcript in which the i-th instance of a detected topic occurs.
`iab_categories_result.results[i].labels[j].relevance`	number	How relevant the j-th detected topic is in the i-th instance of a detected topic.
`iab_categories_result.results[i].labels[j].label`	string	The IAB taxonomical label for the j-th label of the i-th instance of a detected topic, where `>` denotes supertopic/subtopic relationship.
`iab_categories_result.results[i].timestamp.start`	number	The starting time in the audio file at which the i-th detected topic instance is discussed.
`iab_categories_result.results[i].timestamp.end`	number	The ending time in the audio file at which the i-th detected topic instance is discussed.
`iab_categories_result.summary`	object	Summary where each property is a detected topic.
`iab_categories_result.summary.topic`	number	The overall relevance of topic to the entire audio file.

The response also includes the request parameters used to generate the transcript.

Frequently asked questions

How does the Topic Detection model handle misspelled or unrecognized words?

The Topic Detection model uses natural language processing and machine learning to identify related words and phrases even if they are misspelled or unrecognized. However, the accuracy of the detection may depend on the severity of the misspelling or the obscurity of the word.

Can I use the Topic Detection model to identify entities that aren't part of the IAB Taxonomy?

No, the Topic Detection model can only identify entities that are part of the IAB Taxonomy. The model is optimized for contextual targeting use cases, so using the predefined IAB categories ensures the most accurate results.

Why am I not getting any topic predictions for my audio file?

There could be several reasons why you aren’t getting any topic predictions for your audio file. One possible reason is that the audio file doesn’t contain enough relevant content for the model to analyze. Additionally, the accuracy of the predictions may be affected by factors such as background noise, low-quality audio, or a low confidence threshold for topic detection. It’s recommended to review and adjust the model’s configuration parameters and to provide high-quality, relevant audio files for analysis.

Why am I getting inaccurate or irrelevant topic predictions for my audio file?

There could be several reasons why you’re getting inaccurate or irrelevant topic predictions for your audio file. One possible reason is that the audio file contains background noise or other non-relevant content that’s interfering with the model’s analysis. Additionally, the accuracy of the predictions may be affected by factors such as low-quality audio, a low confidence threshold for topic detection, or insufficient training data. It’s recommended to review and adjust the model’s configuration parameters, to provide high-quality, relevant audio files for analysis, and to consider adding additional training data to the model.

Is AssemblyAI associated with IAB?

As of 2023, AssemblyAI is a partner with the Interactive Advertising Bureau (IAB), a certification and community for advertising across the internet. AssemblyAI built Topic Detection using the IAB Taxonomy, which is a blueprint of the approximately 700 topics used to categorize ads.