Translation

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
audio_url = "https://assembly.ai/wildfires.mp3"
12
13
# Configure transcription with translation
14
data = {
15
  "audio_url": audio_url,
16
  "speaker_labels": True,  # Enable speaker labels
17
  # "language_detection": True,  # Enable language detection if you are processing files in a variety of languages
18
  "speech_understanding": {
19
    "request": {
20
      "translation": {
21
        "target_languages": ["es", "de"],  # Translate to Spanish and German
22
        "formal": True  # Use formal language style
23
      }
24
    }
25
  }
26
}
27
28
# Submit 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 transcription results
34
while True:
35
  transcript = requests.get(polling_endpoint, headers=headers).json()
36
37
  if transcript["status"] == "completed":
38
    break
39
40
  elif transcript["status"] == "error":
41
    raise RuntimeError(f"Transcription failed: {transcript['error']}")
42
43
  else:
44
    time.sleep(3)
45
46
# Access and display results
47
print("\n--- Original Transcript ---")
48
print(transcript['text'][:200] + "...\n")
49
50
print("--- Translations ---")
51
for language_code, translated_text in transcript['translated_texts'].items():
52
  print(f"{language_code.upper()}:")
53
  print(translated_text[:200] + "...\n")

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
audio_url = "https://assembly.ai/wildfires.mp3"
12
13
# Submit transcription request (without translation)
14
data = {
15
  "audio_url": audio_url,
16
  "speaker_labels": True,
17
  # "language_detection": True,  # Enable language detection if you are processing files in a variety of languages
18
}
19
20
# Transcribe file
21
response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)
22
transcript_id = response.json()["id"]
23
polling_endpoint = base_url + f"/v2/transcript/{transcript_id}"
24
25
# Poll for transcription completion
26
while True:
27
  transcript = requests.get(polling_endpoint, headers=headers).json()
28
29
  if transcript["status"] == "completed":
30
    print("Transcription completed!")
31
    break
32
33
  elif transcript["status"] == "error":
34
    raise RuntimeError(f"Transcription failed: {transcript['error']}")
35
36
  else:
37
    time.sleep(3)
38
39
# Add translation configuration to the completed transcript
40
understanding_body = {
41
  "transcript_id": transcript_id,
42
  "speech_understanding": {
43
    "request": {
44
      "translation": {
45
      "target_languages": ["es", "de"],  # Translate to Spanish and German
46
      "formal": True  # Use formal language style
47
      }
48
    }
49
  }
50
}
51
52
# Send to Speech Understanding API for translation
53
result = requests.post(
54
  "https://llm-gateway.assemblyai.com/v1/understanding",
55
  headers=headers,
56
  json=understanding_body
57
).json()
58
59
# Access and display results
60
print("\n--- Original Transcript ---")
61
print(transcript['text'][:200] + "...\n")
62
63
print("--- Translations ---")
64
for language_code, translated_text in result['translated_texts'].items():
65
  print(f"{language_code.upper()}:")
66
  print(translated_text[:200] + "...\n")

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 transcription with translation and speaker labels
13
data = {
14
  "audio_url": audio_url,
15
  "speaker_labels": True,  # Enable speaker labels
16
  # "language_detection": True,  # Enable language detection if you are processing files in a variety of languages
17
  "speech_understanding": {
18
    "request": {
19
      "translation": {
20
        "target_languages": ["es"],
21
        "match_original_utterance": True,  # Get translated text per utterance
22
        "formal": True
23
      }
24
    }
25
  }
26
}
27
28
# Submit 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 transcription results
34
while True:
35
  transcript = requests.get(polling_endpoint, headers=headers).json()
36
37
  if transcript["status"] == "completed":
38
    break
39
40
  elif transcript["status"] == "error":
41
    raise RuntimeError(f"Transcription failed: {transcript['error']}")
42
43
  else:
44
    time.sleep(3)
45
46
# Access translated utterances
47
for utterance in transcript["utterances"]:
48
  print(f"Speaker {utterance['speaker']}:")
49
  print(f"  Original: {utterance['text'][:100]}...")
50
  print(f"  Spanish: {utterance['translated_texts']['es'][:100]}...")
51
  print()