Universal-2

Universal-2 offers the broadest language coverage of any AssemblyAI model, supporting high-accuracy transcription across 99 languages with low latency. It supports customization through keyterms prompting (up to 200 words) and includes features like multichannel support, automatic language detection, code switching, speaker diarization, and more. Universal-2 is the go-to choice when you need reliable transcription across diverse languages.

Key capabilities

• 99 language support: Transcribe audio in 99 languages with high accuracy
• Keyterms prompting: Improve recognition of up to 200 domain-specific terms, rare words, and proper nouns
• Automatic language detection: Automatically detect the spoken language in your audio
• Speaker diarization: Identify and label different speakers in the audio
• Multichannel support: Transcribe audio with multiple channels separately
• Code switching: Handle audio that switches between languages

Supported languages

Quickstart

Get started with Universal-2 using the code below. This example transcribes a pre-recorded audio file using the Universal-2 model and prints the transcript text to your terminal.

$
pip install requests

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/wildfires.mp3",
9
    "speech_models": ["universal-2"],
10
    "language_detection": True
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)