Custom Topic Tags Using LLM Gateway

1
import requests
2
import time
3
4
base_url = "https://api.assemblyai.com"
5
headers = {"authorization": "<YOUR_API_KEY>"}
6
7
# Step 1: Transcribe the audio
8
audio_url = "https://storage.googleapis.com/aai-web-samples/meeting.mp4"
9
data = {"audio_url": audio_url}
10
11
response = requests.post(base_url + "/v2/transcript", json=data, headers=headers)
12
transcript_id = response.json()['id']
13
polling_endpoint = base_url + "/v2/transcript/" + transcript_id
14
15
while True:
16
    transcription_result = requests.get(polling_endpoint, headers=headers).json()
17
    if transcription_result['status'] == 'completed':
18
        break
19
    elif transcription_result['status'] == 'error':
20
        raise RuntimeError(f"Transcription failed: {transcription_result['error']}")
21
    else:
22
        time.sleep(3)
23
24
# Step 2: Generate topic tags with LLM Gateway
25
tag_list = {
26
    'Sports': 'News and updates on various athletic events, teams, and sports personalities.',
27
    'Politics': 'Coverage and discussion of government activities, policies, and political events.',
28
    'Entertainment': 'Information on movies, music, television, celebrities, and arts.',
29
    'Technology': 'News and reviews on gadgets, software, tech advancements, and trends.',
30
    'Health': 'Articles focusing on medical news, wellness, and health-related topics.',
31
    'Business': 'Updates on markets, industries, companies, and economic trends.',
32
    'Science': 'News and insights into scientific discoveries, research, and innovations.',
33
    'Education': 'Coverage of topics related to schools, educational policies, and learning.',
34
    'Travel': 'Information on destinations, travel tips, and tourism news.',
35
    'Lifestyle': 'Articles on fashion, hobbies, personal interests, and daily life.',
36
    'Environment': 'News and discussion about environmental issues and sustainability.',
37
    'Finance': 'Information on personal finance, investments, banking, and economic news.',
38
    'World News': 'International news covering global events and issues.',
39
    'Crime': 'Reports and updates on criminal activities, law enforcement, and legal cases.',
40
    'Culture': 'Coverage of cultural events, traditions, and societal norms.'
41
}
42
43
prompt = f"""
44
You are a helpful assistant designed to label video content with topic tags.
45
46
I will give you a list of topics and definitions. Select the most relevant topic from the list. Return your selection and nothing else.
47
48
<topics_list>
49
{tag_list}
50
</topics_list>
51
"""
52
53
llm_gateway_data = {
54
    "model": "claude-sonnet-4-5-20250929",
55
    "messages": [
56
        {"role": "user", "content": f"{prompt}\n\nTranscript: {transcription_result['text']}"}
57
    ],
58
    "max_tokens": 500
59
}
60
61
response = requests.post(
62
    "https://llm-gateway.assemblyai.com/v1/chat/completions",
63
    headers=headers,
64
    json=llm_gateway_data
65
)
66
67
result = response.json()["choices"][0]["message"]["content"]
68
print(result.strip())

1
import requests
2
import time
3
4
base_url = "https://api.assemblyai.com"
5
headers = {"authorization": "<YOUR_API_KEY>"}
6
7
# Transcribe the audio
8
audio_url = "https://storage.googleapis.com/aai-web-samples/meeting.mp4"
9
data = {"audio_url": audio_url}  # You can also use a URL to an audio or video file on the web
10
11
response = requests.post(base_url + "/v2/transcript", json=data, headers=headers)
12
transcript_id = response.json()['id']
13
polling_endpoint = base_url + "/v2/transcript/" + transcript_id
14
15
while True:
16
    transcription_result = requests.get(polling_endpoint, headers=headers).json()
17
    if transcription_result['status'] == 'completed':
18
        break
19
    elif transcription_result['status'] == 'error':
20
        raise RuntimeError(f"Transcription failed: {transcription_result['error']}")
21
    else:
22
        time.sleep(3)

1
tag_list = {
2
    'Sports': 'News and updates on various athletic events, teams, and sports personalities.',
3
    'Politics': 'Coverage and discussion of government activities, policies, and political events.',
4
    'Entertainment': 'Information on movies, music, television, celebrities, and arts.',
5
    'Technology': 'News and reviews on gadgets, software, tech advancements, and trends.',
6
    'Health': 'Articles focusing on medical news, wellness, and health-related topics.',
7
    'Business': 'Updates on markets, industries, companies, and economic trends.',
8
    'Science': 'News and insights into scientific discoveries, research, and innovations.',
9
    'Education': 'Coverage of topics related to schools, educational policies, and learning.',
10
    'Travel': 'Information on destinations, travel tips, and tourism news.',
11
    'Lifestyle': 'Articles on fashion, hobbies, personal interests, and daily life.',
12
    'Environment': 'News and discussion about environmental issues and sustainability.',
13
    'Finance': 'Information on personal finance, investments, banking, and economic news.',
14
    'World News': 'International news covering global events and issues.',
15
    'Crime': 'Reports and updates on criminal activities, law enforcement, and legal cases.',
16
    'Culture': 'Coverage of cultural events, traditions, and societal norms.'
17
}

1
tag_list = {
2
    'Account Issues': 'Problems related to user accounts, such as login difficulties or account access.',
3
    'Technical Support': 'Inquiries regarding software or hardware functionality and troubleshooting.',
4
    'Billing and Payments': 'Questions or problems about invoices, payments, or subscription plans.',
5
    'Product Inquiry': 'Requests for information about product features, capabilities, or availability.',
6
    'Service Disruption': 'Reports of outages or interruptions in service performance or availability.'
7
}

1
prompt = f"""
2
You are a helpful assistant designed to label video content with topic tags.
3
4
I will give you a list of topics and definitions. Select the most relevant topic from the list. Return your selection and nothing else.
5
6
<topics_list>
7
{tag_list}
8
</topics_list>
9
"""
10
11
llm_gateway_data = {
12
    "model": "claude-sonnet-4-5-20250929",
13
    "messages": [
14
        {"role": "user", "content": f"{prompt}\n\nTranscript: {transcription_result['text']}"}
15
    ],
16
    "max_tokens": 500
17
}
18
19
response = requests.post(
20
    "https://llm-gateway.assemblyai.com/v1/chat/completions",
21
    headers=headers,
22
    json=llm_gateway_data
23
)
24
25
result = response.json()["choices"][0]["message"]["content"]
26
print(result.strip())