Improving Transcript Accuracy | AssemblyAI

Using Slam-1 (Recommended)

Improve transcription accuracy by leveraging Slam-1’s contextual understanding capabilities by prompting the model with certain words or phrases that are likely to appear frequently in your audio file.

Rather than simply increasing the likelihood of detecting specific words, Slam-1’s multi-modal architecture actually understands the semantic meaning and context of the terminology you provide, enhancing transcription quality not just of the exact terms you specify, but also related terminology, variations, and contextually similar phrases.

Provide up to 1000 domain-specific words or phrases (maximum 6 words per phrase) that may appear in your audio using the optional keyterms_prompt parameter:

Python

JavaScript

1 import requests
2 import time
3 
4 base_url = "https://api.assemblyai.com"
5 headers = {"authorization": "<YOUR_API_KEY>"}
6 
7 data = {
8     "audio_url": "https://assembly.ai/sports_injuries.mp3",
9     "speech_model": "slam-1",
10     "keyterms_prompt": ['differential diagnosis', 'hypertension', 'Wellbutrin XL 150mg']
11 }
12 
13 response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
14 
15 if response.status_code != 200:
16     print(f"Error: {response.status_code}, Response: {response.text}")
17     response.raise_for_status()
18 
19 transcript_response = response.json()
20 transcript_id = transcript_response["id"]
21 polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
22 
23 while True:
24     transcript = requests.get(polling_endpoint, headers=headers).json()
25     if transcript["status"] == "completed":
26         print(transcript["text"])
27         break
28     elif transcript["status"] == "error":
29         raise RuntimeError(f"Transcription failed: {transcript['error']}")
30     else:
31         time.sleep(3)

Keyword count limits

While we support up to 1000 key words and phrases, actual capacity may be lower due to internal tokenization and implementation constraints. Key points to remember:

Each word in a multi-word phrase counts towards the 1000 keyword limit
Capitalization affects capacity (uppercase tokens consume more than lowercase)
Longer words consume more capacity than shorter words

For optimal results, use shorter phrases when possible and be mindful of your total token count when approaching the keyword limit.

Using Universal (Beta)

keyterms_prompt for Universal is currently available at no additional cost while we gather feedback and refine functionality. Pricing may be introduced as the feature moves out of beta. We’ll notify all users well in advance of any pricing changes.

As we continue to develop this feature, functionality may evolve. For the latest updates and code examples, please check back on this page.

If you’re currently using our universal model, the keyterms_prompt parameter is in Beta for English files.

The maximum number of keyterms with Universal is 200. Keyterms shorter than 5 characters or longer than 50 characters are ignored.

Python

JavaScript

1 import requests
2 import time
3 
4 base_url = "https://api.assemblyai.com"
5 headers = {"authorization": "<YOUR_API_KEY>"}
6 
7 data = {
8     "audio_url": "https://assembly.ai/sports_injuries.mp3",
9     "speech_model": "universal",
10     "keyterms_prompt": ['differential diagnosis', 'hypertension', 'Wellbutrin XL 150mg']
11 }
12 
13 response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
14 
15 if response.status_code != 200:
16     print(f"Error: {response.status_code}, Response: {response.text}")
17     response.raise_for_status()
18 
19 transcript_response = response.json()
20 transcript_id = transcript_response["id"]
21 polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
22 
23 while True:
24     transcript = requests.get(polling_endpoint, headers=headers).json()
25     if transcript["status"] == "completed":
26         print(transcript["text"])
27         break
28     elif transcript["status"] == "error":
29         raise RuntimeError(f"Transcription failed: {transcript['error']}")
30     else:
31         time.sleep(3)