Speaker Diarization

1
import assemblyai as aai
2
3
aai.settings.api_key = "<YOUR_API_KEY>"
4
5
# You can use a local filepath:
6
# audio_file = "./example.mp3"
7
8
# Or use a publicly-accessible URL:
9
audio_file = (
10
    "https://assembly.ai/wildfires.mp3"
11
)
12
13
config = aai.TranscriptionConfig(
14
  speech_models=["universal-3-pro", "universal-2"],
15
  language_detection=True,
16
  speaker_labels=True,
17
)
18
19
transcript = aai.Transcriber().transcribe(audio_file, config)
20
21
for utterance in transcript.utterances:
22
  print(f"Speaker {utterance.speaker}: {utterance.text}")

1
import assemblyai as aai
2
3
aai.settings.api_key = "<YOUR_API_KEY>"
4
5
# You can use a local filepath:
6
# audio_file = "./example.mp3"
7
8
# Or use a publicly-accessible URL:
9
audio_file = (
10
    "https://assembly.ai/wildfires.mp3"
11
)
12
13
config = aai.TranscriptionConfig(
14
  speech_models=["universal-3-pro", "universal-2"],
15
  language_detection=True,
16
  speaker_labels=True,
17
  speakers_expected=5,
18
)
19
20
transcript = aai.Transcriber().transcribe(audio_file, config)
21
22
for utterance in transcript.utterances:
23
  print(f"Speaker {utterance.speaker}: {utterance.text}")

1
import assemblyai as aai
2
3
aai.settings.api_key = "<YOUR_API_KEY>"
4
5
# You can use a local filepath:
6
# audio_file = "./example.mp3"
7
8
# Or use a publicly-accessible URL:
9
audio_file = (
10
    "https://assembly.ai/wildfires.mp3"
11
)
12
13
config = aai.TranscriptionConfig(
14
  speech_models=["universal-3-pro", "universal-2"],
15
  language_detection=True,
16
  speaker_labels=True,
17
  speaker_options=aai.SpeakerOptions(
18
    min_speakers_expected=3,
19
    max_speakers_expected=5
20
  ),
21
)
22
23
transcript = aai.Transcriber().transcribe(audio_file, config)
24
25
for utterance in transcript.utterances:
26
  print(f"Speaker {utterance.speaker}: {utterance.text}")

1
import requests
2
import time
3
4
base_url = "https://api.assemblyai.com"
5
6
headers = {
7
    "authorization": "<YOUR_API_KEY>"
8
}
9
10
audio_url = "https://assembly.ai/wildfires.mp3"
11
12
# Configure transcript with speaker diarization and speaker identification
13
data = {
14
    "audio_url": audio_url,
15
    "speech_models": ["universal-3-pro", "universal-2"],
16
    "language_detection": True,
17
    "speaker_labels": True,
18
    "speech_understanding": {
19
        "request": {
20
            "speaker_identification": {
21
                "speaker_type": "name",
22
                "known_values": ["Michel Martin", "Peter DeCarlo"]
23
            }
24
        }
25
    }
26
}
27
28
# Submit the transcription request
29
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
30
transcript_id = response.json()["id"]
31
polling_endpoint = base_url + f"/v2/transcript/{transcript_id}"
32
33
# Poll for transcription results
34
while True:
35
    transcript = requests.get(polling_endpoint, headers=headers).json()
36
37
    if transcript["status"] == "completed":
38
        break
39
    elif transcript["status"] == "error":
40
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
41
    else:
42
        time.sleep(3)
43
44
# Print utterances with identified speaker names
45
for utterance in transcript["utterances"]:
46
    print(f"{utterance['speaker']}: {utterance['text']}")