Apply LLM Gateway to Audio Transcripts

Overview

A Large Language Model (LLM) is a machine learning model that uses natural language processing (NLP) to generate text. LLM Gateway is a unified API that provides access to 25+ models from Claude, GPT, Gemini, and more through a single interface. You can use LLM Gateway to analyze audio transcripts, for example to ask questions about a call, or to summarize a meeting.

By the end of this tutorial, you’ll be able to use LLM Gateway to summarize an audio file.

Here’s the full sample code for what you’ll build in this tutorial:

1
import requests
2
import time
3
4
# Step 1: Transcribe the audio
5
base_url = "https://api.assemblyai.com"
6
7
headers = {
8
  "authorization": "<YOUR_API_KEY>"
9
}
10
11
# You can use a local filepath:
12
# with open("./my-audio.mp3", "rb") as f:
13
# response = requests.post(base_url + "/v2/upload",
14
# headers=headers,
15
# data=f)
16
# upload_url = response.json()["upload_url"]
17
# Or use a publicly-accessible URL:
18
19
upload_url = "https://assembly.ai/sports_injuries.mp3"
20
21
data = {
22
  "audio_url": upload_url
23
}
24
25
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
26
27
transcript_id = response.json()["id"]
28
polling_endpoint = base_url + f"/v2/transcript/{transcript_id}"
29
30
while True:
31
  transcript = requests.get(polling_endpoint, headers=headers).json()
32
33
  if transcript["status"] == "completed":
34
    break
35
36
  elif transcript["status"] == "error":
37
    raise RuntimeError(f"Transcription failed: {transcript['error']}")
38
39
  else:
40
    time.sleep(3)
41
42
# Step 2: Send transcript to LLM Gateway
43
prompt = "Provide a brief summary of the transcript."
44
45
llm_gateway_data = {
46
  "model": "claude-sonnet-4-6",
47
  "messages": [
48
    {"role": "user", "content": f"{prompt}\n\n{{{{ transcript }}}}"}
49
  ],
50
  "transcript_id": transcript_id,
51
  "max_tokens": 1000
52
}
53
54
response = requests.post(
55
  "https://llm-gateway.assemblyai.com/v1/chat/completions",
56
  headers=headers,
57
  json=llm_gateway_data
58
)
59
print(response.json()["choices"][0]["message"]["content"])

If you run the code above, you’ll see the following output:

1
The transcript describes several common sports injuries - runner's knee,
2
sprained ankle, meniscus tear, rotator cuff tear, and ACL tear. It provides
3
definitions, causes, and symptoms for each injury. The transcript seems to be
4
narrating sports footage and describing injuries as they occur to the athletes.
5
Overall, it provides an overview of these common sports injuries that can result
6
from overuse or sudden trauma during athletic activities

Before you begin

To complete this tutorial, you need:

• Python or Node installed.
• An AssemblyAI account with a credit card set up.
• Basic understanding of how to Transcribe an audio file.

Step 1: Install prerequisites

$
pip install requests

Step 2: Transcribe an audio file

When you pass transcript_id to LLM Gateway and include the {{ transcript }} tag in a message, the API substitutes the tag with the transcript’s text field before running the completion. It does not include other fields such as utterances or speaker labels. If you need speaker-separated context, format the utterances yourself and include them in your prompt.

In this step, you’ll transcribe an audio file that you can later use with LLM Gateway.

For more information about transcribing audio, see Transcribe an audio file.

1
import requests
2
import time
3
4
base_url = "https://api.assemblyai.com"
5
6
headers = {"authorization": "<YOUR_API_KEY>"}
7
8
# You can use a local filepath:
9
# with open("./my-audio.mp3", "rb") as f:
10
#     response = requests.post(base_url + "/v2/upload", headers=headers, data=f)
11
#     upload_url = response.json()["upload_url"]
12
13
# Or use a publicly-accessible URL:
14
upload_url = "https://assembly.ai/sports_injuries.mp3"
15
16
data = {"audio_url": upload_url}
17
18
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
19
20
transcript_id = response.json()["id"]
21
polling_endpoint = base_url + f"/v2/transcript/{transcript_id}"
22
23
while True:
24
    transcript = requests.get(polling_endpoint, headers=headers).json()
25
26
    if transcript["status"] == "completed":
27
        break
28
29
    elif transcript["status"] == "error":
30
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
31
32
    else:
33
        time.sleep(3)

1
transcript = requests.get("https://api.assemblyai.com/v2/transcript/YOUR_TRANSCRIPT_ID", headers=headers).json()

Step 3: Send transcript to LLM Gateway

In this step, you’ll send the transcript ID to LLM Gateway along with a prompt to generate text output.

The prompt is a text string that provides the LLM with instructions on how to generate the text output. You’ll write a prompt that references the transcript with a {{ transcript }} tag and send it to LLM Gateway using the chat completions API. Pass the transcript ID as the top-level transcript_id field — the API substitutes the tag with the transcript’s text before running the completion.

1
prompt = "Provide a brief summary of the transcript."

1
llm_gateway_data = {
2
  "model": "claude-sonnet-4-6",
3
  "messages": [
4
    {"role": "user", "content": f"{prompt}\n\n{{{{ transcript }}}}"}
5
  ],
6
  "transcript_id": transcript_id,
7
  "max_tokens": 1000
8
}
9
10
result = requests.post(
11
  "https://llm-gateway.assemblyai.com/v1/chat/completions",
12
  headers=headers,
13
  json=llm_gateway_data
14
)

1
print(result.json()["choices"][0]["message"]["content"])

 The transcript describes several common sports injuries - runner's knee,
 sprained ankle, meniscus tear, rotator cuff tear, and ACL tear. It provides
 definitions, causes, and symptoms for each injury. The transcript seems to be
 narrating sports footage and describing injuries as they occur to the athletes.
 Overall, it provides an overview of these common sports injuries that can
 result from overuse or sudden trauma during athletic activities

Next steps

In this tutorial, you’ve learned how to generate LLM output based on your audio transcripts using LLM Gateway. The type of output depends on your prompt, so try exploring different prompts to see how they affect the output. Here’s a few more prompts to try.

• “Provide an analysis of the transcript and offer areas to improve with exact quotes.”
• “What’s the main take-away from the transcript?”
• “Generate a set of action items from this transcript.”

To learn more about LLM Gateway and working with different models, see the following resources:

• LLM Gateway Overview
• Basic Chat Completions
• Multi-turn Conversations

Need some help?

If you get stuck, or have any other questions, we’d love to help you out. Contact our support team at support@assemblyai.com or create a support ticket.