Audio Intelligence

1
import assemblyai as aai
2
3
aai.settings.api_key = "<YOUR_API_KEY>"
4
5
# audio_file = "./local_file.mp3"
6
audio_file = "https://assembly.ai/wildfires.mp3"
7
8
config = aai.TranscriptionConfig(auto_chapters=True)
9
10
transcript = aai.Transcriber().transcribe(audio_file, config)
11
12
for chapter in transcript.chapters:
13
  print(f"{chapter.start}-{chapter.end}: {chapter.headline}")

1
import assemblyai as aai
2
3
aai.settings.api_key = "<YOUR_API_KEY>"
4
5
# audio_file = "./local_file.mp3"
6
audio_file = "https://assembly.ai/wildfires.mp3"
7
8
config = aai.TranscriptionConfig(content_safety=True)
9
10
transcript = aai.Transcriber().transcribe(audio_file, config)
11
12
# Get the parts of the transcript which were flagged as sensitive.
13
for result in transcript.content_safety.results:
14
    print(result.text)
15
    print(f"Timestamp: {result.timestamp.start} - {result.timestamp.end}")
16
17
    # Get category, confidence, and severity.
18
    for label in result.labels:
19
      print(f"{label.label} - {label.confidence} - {label.severity}")  # content safety category
20
    print()
21
22
# Get the confidence of the most common labels in relation to the entire audio file.
23
for label, confidence in transcript.content_safety.summary.items():
24
    print(f"{confidence * 100}% confident that the audio contains {label}")
25
26
print()
27
28
# Get the overall severity of the most common labels in relation to the entire audio file.
29
for label, severity_confidence in transcript.content_safety.severity_score_summary.items():
30
    print(f"{severity_confidence.low * 100}% confident that the audio contains low-severity {label}")
31
    print(f"{severity_confidence.medium * 100}% confident that the audio contains medium-severity {label}")
32
    print(f"{severity_confidence.high * 100}% confident that the audio contains high-severity {label}")

1
# Setting the content safety confidence threshold to 60%.
2
config = aai.TranscriptionConfig(
3
  content_safety=True,
4
  content_safety_confidence=60
5
)

1
import assemblyai as aai
2
3
aai.settings.api_key = "<YOUR_API_KEY>"
4
5
# audio_file = "./local_file.mp3"
6
audio_file = "https://assembly.ai/wildfires.mp3"
7
8
config = aai.TranscriptionConfig(entity_detection=True)
9
10
transcript = aai.Transcriber().transcribe(audio_file, config)
11
12
for entity in transcript.entities:
13
    print(entity.text)
14
    print(entity.entity_type)
15
    print(f"Timestamp: {entity.start} - {entity.end}\n")

1
import assemblyai as aai
2
3
aai.settings.api_key = "<YOUR_API_KEY>"
4
5
# audio_file = "./local_file.mp3"
6
audio_file = "https://assembly.ai/wildfires.mp3"
7
8
config = aai.TranscriptionConfig(auto_highlights=True)
9
10
transcript = aai.Transcriber().transcribe(audio_file, config)
11
12
for result in transcript.auto_highlights.results:
13
    print(f"Highlight: {result.text}, Count: {result.count}, Rank: {result.rank}, Timestamps: {result.timestamps}")

1
import assemblyai as aai
2
3
aai.settings.api_key = "<YOUR_API_KEY>"
4
5
# audio_file = "./local_file.mp3"
6
audio_file = "https://assembly.ai/wildfires.mp3"
7
8
config = aai.TranscriptionConfig().set_redact_pii(
9
    policies=[
10
        aai.PIIRedactionPolicy.person_name,
11
        aai.PIIRedactionPolicy.organization,
12
        aai.PIIRedactionPolicy.occupation,
13
    ],
14
    substitution=aai.PIISubstitutionPolicy.hash,
15
)
16
17
transcript = aai.Transcriber().transcribe(audio_file, config)
18
19
print(transcript.text)

1
import assemblyai as aai
2
3
aai.settings.api_key = "<YOUR_API_KEY>"
4
5
# audio_file = "./local_file.mp3"
6
audio_file = "https://assembly.ai/wildfires.mp3"
7
8
config = aai.TranscriptionConfig(sentiment_analysis=True)
9
10
transcript = aai.Transcriber().transcribe(audio_file, config)
11
12
for sentiment_result in transcript.sentiment_analysis:
13
    print(sentiment_result.text)
14
    print(sentiment_result.sentiment)  # POSITIVE, NEUTRAL, or NEGATIVE
15
    print(sentiment_result.confidence)
16
    print(f"Timestamp: {sentiment_result.start} - {sentiment_result.end}")

1
config = aai.TranscriptionConfig(
2
  sentiment_analysis=True,
3
  speaker_labels=True
4
)
5
6
# ...
7
8
for sentiment_result in transcript.sentiment_analysis:
9
  print(sentiment_result.speaker)

1
import assemblyai as aai
2
3
aai.settings.api_key = "<YOUR_API_KEY>"
4
5
# audio_file = "./local_file.mp3"
6
audio_file = "https://assembly.ai/wildfires.mp3"
7
8
config = aai.TranscriptionConfig(
9
  summarization=True,
10
  summary_model=aai.SummarizationModel.informative,
11
  summary_type=aai.SummarizationType.bullets
12
)
13
14
transcript = aai.Transcriber().transcribe(audio_file, config)
15
16
print(transcript.summary)

1
import assemblyai as aai
2
3
aai.settings.api_key = "<YOUR_API_KEY>"
4
5
# audio_file = "./local_file.mp3"
6
audio_file = "https://assembly.ai/wildfires.mp3"
7
8
config = aai.TranscriptionConfig(iab_categories=True)
9
10
transcript = aai.Transcriber().transcribe(audio_file, config)
11
12
# Get the parts of the transcript that were tagged with topics
13
for result in transcript.iab_categories.results:
14
    print(result.text)
15
    print(f"Timestamp: {result.timestamp.start} - {result.timestamp.end}")
16
    for label in result.labels:
17
        print(f"{label.label} ({label.relevance})")
18
19
# Get a summary of all topics in the transcript
20
for topic, relevance in transcript.iab_categories.summary.items():
21
    print(f"Audio is {relevance * 100}% relevant to {topic}")