Auto Chapters

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 your audio file
8
audio_url = "https://assembly.ai/wildfires.mp3"
9
10
data = {
11
    "audio_url": audio_url,
12
    "speech_models": ["universal-3-pro", "universal-2"],
13
    "language_detection": True
14
}
15
16
response = requests.post(base_url + "/v2/transcript", json=data, headers=headers)
17
transcript_id = response.json()['id']
18
polling_endpoint = base_url + "/v2/transcript/" + transcript_id
19
20
while True:
21
    transcription_result = requests.get(polling_endpoint, headers=headers).json()
22
    if transcription_result['status'] == 'completed':
23
        break
24
    elif transcription_result['status'] == 'error':
25
        raise RuntimeError(f"Transcription failed: {transcription_result['error']}")
26
    else:
27
        time.sleep(3)
28
29
# Step 2: Get paragraphs from the transcript
30
paragraphs = requests.get(polling_endpoint + '/paragraphs', headers=headers).json()['paragraphs']
31
32
# Step 3: Combine paragraphs into groups for chapter summaries
33
combined_paragraphs = []
34
step = 2  # Adjust to control chapter length
35
36
for i in range(0, len(paragraphs), step):
37
    paragraph_group = paragraphs[i : i + step]
38
    start = paragraph_group[0]['start']
39
    end = paragraph_group[-1]['end']
40
    text = " ".join(p['text'] for p in paragraph_group)
41
    combined_paragraphs.append({"text": text, "start": start, "end": end})
42
43
# Step 4: Generate chapter summaries with LLM Gateway
44
for chapter in combined_paragraphs:
45
    llm_gateway_data = {
46
        "model": "claude-sonnet-4-6",
47
        "messages": [
48
            {"role": "user", "content": f"Provide a brief one-paragraph summary, a one-line gist, and a headline for this section of a transcript.\n\nText: {chapter['text']}"}
49
        ],
50
        "max_tokens": 500
51
    }
52
53
    response = requests.post(
54
        "https://llm-gateway.assemblyai.com/v1/chat/completions",
55
        headers=headers,
56
        json=llm_gateway_data
57
    )
58
59
    result = response.json()["choices"][0]["message"]["content"]
60
    print(f"{chapter['start']}-{chapter['end']}: {result}\n")