Introducing Universal-3 Pro

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
    "language_detection": True,
10
    "speech_models": ["universal-3-pro", "universal-2"]
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)

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://assemblyaiassets.com/audios/keyterms_prompting.wav",
9
    "language_detection": True,
10
    "speech_models": ["universal-3-pro", "universal-2"],
11
    "keyterms_prompt": ["Kelly Byrne-Donoghue"]
12
}
13
14
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
15
16
if response.status_code != 200:
17
    print(f"Error: {response.status_code}, Response: {response.text}")
18
    response.raise_for_status()
19
20
transcript_response = response.json()
21
transcript_id = transcript_response["id"]
22
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
23
24
while True:
25
    transcript = requests.get(polling_endpoint, headers=headers).json()
26
    if transcript["status"] == "completed":
27
        print(transcript["text"])
28
        break
29
    elif transcript["status"] == "error":
30
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
31
    else:
32
        time.sleep(3)

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://assemblyaiassets.com/audios/verbatim.mp3",
9
    "language_detection": True,
10
    "speech_models": ["universal-3-pro", "universal-2"],
11
    "prompt": "Produce a transcript suitable for conversational analysis. Every disfluency is meaningful data. Include: fillers (um, uh, er, ah, hmm, mhm, like, you know, I mean), repetitions (I I, the the), restarts (I was- I went), stutters (th-that, b-but, no-not), and informal speech (gonna, wanna, gotta)"
12
}
13
14
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
15
16
if response.status_code != 200:
17
    print(f"Error: {response.status_code}, Response: {response.text}")
18
    response.raise_for_status()
19
20
transcript_response = response.json()
21
transcript_id = transcript_response["id"]
22
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
23
24
while True:
25
    transcript = requests.get(polling_endpoint, headers=headers).json()
26
    if transcript["status"] == "completed":
27
        print(transcript["text"])
28
        break
29
    elif transcript["status"] == "error":
30
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
31
    else:
32
        time.sleep(3)

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://assemblyaiassets.com/audios/ouput_formatting.mp3",
9
    "language_detection": True,
10
    "speech_models": ["universal-3-pro", "universal-2"],
11
    "prompt": "Add punctuation based on the speaker's tone and expressiveness. Use exclamation marks (!) when the speaker is yelling, excited, or emphatic. Use question marks (?) for questioning intonation. Apply standard punctuation (periods, commas) based on natural speech patterns and pauses."
12
}
13
14
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
15
16
if response.status_code != 200:
17
    print(f"Error: {response.status_code}, Response: {response.text}")
18
    response.raise_for_status()
19
20
transcript_response = response.json()
21
transcript_id = transcript_response["id"]
22
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
23
24
while True:
25
    transcript = requests.get(polling_endpoint, headers=headers).json()
26
    if transcript["status"] == "completed":
27
        print(transcript["text"])
28
        break
29
    elif transcript["status"] == "error":
30
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
31
    else:
32
        time.sleep(3)

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://assemblyaiassets.com/audios/nlp_prompting.mp3",
9
    "language_detection": True,
10
    "speech_models": ["universal-3-pro", "universal-2"],
11
    "prompt": "Produce a transcript for a clinical history evaluation. It's important to capture medication and dosage accurately. Every disfluency is meaningful data. Include: fillers (um, uh, er, erm, ah, hmm, mhm, like, you know, I mean), repetitions (I I I, the the), restarts (I was- I went), stutters (th-that, b-but, no-not), and informal speech (gonna, wanna, gotta)"
12
}
13
14
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
15
16
if response.status_code != 200:
17
    print(f"Error: {response.status_code}, Response: {response.text}")
18
    response.raise_for_status()
19
20
transcript_response = response.json()
21
transcript_id = transcript_response["id"]
22
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
23
24
while True:
25
    transcript = requests.get(polling_endpoint, headers=headers).json()
26
    if transcript["status"] == "completed":
27
        print(transcript["text"])
28
        break
29
    elif transcript["status"] == "error":
30
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
31
    else:
32
        time.sleep(3)

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://assemblyaiassets.com/audios/entity_accuracy.mp3",
9
    "language_detection": True,
10
    "speech_models": ["universal-3-pro", "universal-2"],
11
    "prompt": "The speaker is discussing the cancer drug Anktiva (spelled A-N-K-T-I-V-A). When you hear what sounds like Entiva or similar pronunciations, transcribe it as Anktiva. This is the correct pharmaceutical name."
12
}
13
14
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
15
16
if response.status_code != 200:
17
    print(f"Error: {response.status_code}, Response: {response.text}")
18
    response.raise_for_status()
19
20
transcript_response = response.json()
21
transcript_id = transcript_response["id"]
22
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
23
24
while True:
25
    transcript = requests.get(polling_endpoint, headers=headers).json()
26
    if transcript["status"] == "completed":
27
        print(transcript["text"])
28
        break
29
    elif transcript["status"] == "error":
30
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
31
    else:
32
        time.sleep(3)

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://assemblyaiassets.com/audios/speaker_diarization.mp3",
9
    "language_detection": True,
10
    "speech_models": ["universal-3-pro", "universal-2"],
11
    "speaker_labels": True,
12
    "prompt": "Produce a transcript with every disfluency data. Additionally, label speakers with their respective roles. 1. Place [Speaker:role] at the start of each speaker turn. Example format: [Speaker:NURSE] Hello there. How can I help you today? [Speaker:PATIENT] I'm feeling unwell. I have a headache."
13
}
14
15
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
16
17
if response.status_code != 200:
18
    print(f"Error: {response.status_code}, Response: {response.text}")
19
    response.raise_for_status()
20
21
transcript_response = response.json()
22
transcript_id = transcript_response["id"]
23
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
24
25
while True:
26
    transcript = requests.get(polling_endpoint, headers=headers).json()
27
    if transcript["status"] == "completed":
28
        for utterance in transcript["utterances"]:
29
            print(f"Speaker {utterance['speaker']}: {utterance['text']}")
30
        break
31
    elif transcript["status"] == "error":
32
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
33
    else:
34
        time.sleep(3)

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://assemblyaiassets.com/audios/audio_tag.mp3",
9
    "language_detection": True,
10
    "speech_models": ["universal-3-pro", "universal-2"],
11
    "prompt": "Produce a transcript suitable for conversational analysis. Every disfluency is meaningful data. Include: Tag sounds: [beep]"
12
}
13
14
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
15
16
if response.status_code != 200:
17
    print(f"Error: {response.status_code}, Response: {response.text}")
18
    response.raise_for_status()
19
20
transcript_response = response.json()
21
transcript_id = transcript_response["id"]
22
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
23
24
while True:
25
    transcript = requests.get(polling_endpoint, headers=headers).json()
26
    if transcript["status"] == "completed":
27
        print(transcript["text"])
28
        break
29
    elif transcript["status"] == "error":
30
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
31
    else:
32
        time.sleep(3)

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://assemblyaiassets.com/audios/code_switching_multilingual.mp3",
9
    "language_detection": True,
10
    "speech_models": ["universal-3-pro", "universal-2"],
11
    "prompt": "The spoken language may change throughout the audio, transcribe in the original language mix (code-switching), preserving the words in the language they are spoken."
12
}
13
14
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
15
16
if response.status_code != 200:
17
    print(f"Error: {response.status_code}, Response: {response.text}")
18
    response.raise_for_status()
19
20
transcript_response = response.json()
21
transcript_id = transcript_response["id"]
22
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
23
24
while True:
25
    transcript = requests.get(polling_endpoint, headers=headers).json()
26
    if transcript["status"] == "completed":
27
        print(transcript["text"])
28
        break
29
    elif transcript["status"] == "error":
30
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
31
    else:
32
        time.sleep(3)

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://assemblyaiassets.com/audios/verbatim.mp3",
9
    "language_detection": True,
10
    "speech_models": ["universal-3-pro", "universal-2"],
11
    "prompt": "Transcribe with numbers normalized to standard formats. For example, when you see $1 billion, convert to $1,000,000,000."
12
}
13
14
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
15
16
if response.status_code != 200:
17
    print(f"Error: {response.status_code}, Response: {response.text}")
18
    response.raise_for_status()
19
20
transcript_response = response.json()
21
transcript_id = transcript_response["id"]
22
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
23
24
while True:
25
    transcript = requests.get(polling_endpoint, headers=headers).json()
26
    if transcript["status"] == "completed":
27
        print(transcript["text"])
28
        break
29
    elif transcript["status"] == "error":
30
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
31
    else:
32
        time.sleep(3)

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://assemblyaiassets.com/audios/verbatim.mp3",
9
    "language_detection": True,
10
    "speech_models": ["universal-3-pro", "universal-2"],
11
    "prompt": "When multiple speakers talk simultaneously, mark crosstalk segments."
12
}
13
14
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
15
16
if response.status_code != 200:
17
    print(f"Error: {response.status_code}, Response: {response.text}")
18
    response.raise_for_status()
19
20
transcript_response = response.json()
21
transcript_id = transcript_response["id"]
22
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
23
24
while True:
25
    transcript = requests.get(polling_endpoint, headers=headers).json()
26
    if transcript["status"] == "completed":
27
        print(transcript["text"])
28
        break
29
    elif transcript["status"] == "error":
30
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
31
    else:
32
        time.sleep(3)

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://assemblyaiassets.com/audios/nlp_prompting.mp3",
9
    "language_detection": True,
10
    "speech_models": ["universal-3-pro", "universal-2"],
11
    "prompt": "Produce a transcript for a clinical history evaluation. It's important to capture medication and dosage accurately. Every disfluency is meaningful data. Include: fillers (um, uh, er, erm, ah, hmm, mhm, like, you know, I mean), repetitions (I I I, the the), restarts (I was- I went), stutters (th-that, b-but, no-not), and informal speech (gonna, wanna, gotta)",
12
    "temperature": 0.1
13
}
14
15
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
16
17
if response.status_code != 200:
18
    print(f"Error: {response.status_code}, Response: {response.text}")
19
    response.raise_for_status()
20
21
transcript_response = response.json()
22
transcript_id = transcript_response["id"]
23
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"
24
25
while True:
26
    transcript = requests.get(polling_endpoint, headers=headers).json()
27
    if transcript["status"] == "completed":
28
        print(transcript["text"])
29
        break
30
    elif transcript["status"] == "error":
31
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
32
    else:
33
        time.sleep(3)