Speaker Identification

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
# Need to transcribe a local file? Learn more here: https://www.assemblyai.com/docs/getting-started/transcribe-an-audio-file
11
upload_url = "https://assembly.ai/wildfires.mp3"
12
13
# Configure transcript with speaker identification
14
data = {
15
  "audio_url": upload_url,
16
  "speaker_labels": True,
17
  "speech_understanding": {
18
    "request": {
19
      "speaker_identification": {
20
        "speaker_type": "name",
21
        "known_values": ["Michel Martin", "Peter DeCarlo"]  # Change these values to match the names of the speakers in your file
22
      }
23
    }
24
  }
25
}
26
27
# Submit the transcription request
28
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
29
transcript_id = response.json()["id"]
30
polling_endpoint = base_url + f"/v2/transcript/{transcript_id}"
31
32
# Poll for transcription results
33
while True:
34
  transcript = requests.get(polling_endpoint, headers=headers).json()
35
36
  if transcript["status"] == "completed":
37
    break
38
39
  elif transcript["status"] == "error":
40
    raise RuntimeError(f"Transcription failed: {transcript['error']}")
41
42
  else:
43
    time.sleep(3)
44
45
# Access the results and print utterances to the terminal
46
for utterance in transcript["utterances"]:
47
  print(f"{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
# Need to transcribe a local file? Learn more here: https://www.assemblyai.com/docs/getting-started/transcribe-an-audio-file
11
upload_url = "https://assembly.ai/wildfires.mp3"
12
13
data = {
14
  "audio_url": upload_url,
15
  "speaker_labels": True
16
}
17
18
# Transcribe file
19
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
20
21
transcript_id = response.json()["id"]
22
polling_endpoint = base_url + f"/v2/transcript/{transcript_id}"
23
24
# Poll for transcription results
25
while True:
26
  transcript = requests.get(polling_endpoint, headers=headers).json()
27
28
  if transcript["status"] == "completed":
29
    break
30
31
  elif transcript["status"] == "error":
32
    raise RuntimeError(f"Transcription failed: {transcript['error']}")
33
34
  else:
35
    time.sleep(3)
36
37
# Enable speaker identification
38
understanding_body = {
39
  "transcript_id": transcript_id,
40
  "speech_understanding": {
41
    "request": {
42
      "speaker_identification": {
43
        "speaker_type": "name",
44
        "known_values": ["Michel Martin", "Peter DeCarlo"]  # Change these values to match the names of the speakers in your file
45
      }
46
    }
47
  }
48
}
49
50
# Send the modified transcript to the Speech Understanding API
51
result = requests.post(
52
  "https://llm-gateway.assemblyai.com/v1/understanding",
53
  headers = headers,
54
  json = understanding_body
55
).json()
56
57
# Access the results and print utterances to the terminal
58
for utterance in result["utterances"]:
59
  print(f"{utterance['speaker']}: {utterance['text']}")