Python API

from augent import transcribe_audio
 
result = transcribe_audio("podcast.mp3", model_size="tiny")
print(result["text"])
print(result["duration"])
print(result["segments"])

from augent import search_audio
 
matches = search_audio("podcast.mp3", ["funding", "revenue"])
for keyword, hits in matches.items():
    for hit in hits:
        print(f"[{hit['timestamp']}] {hit['snippet']}")

from augent import search_audio_proximity
 
matches = search_audio_proximity(
    "interview.mp3",
    keyword1="problem",
    keyword2="solution",
    max_distance=30
)

from augent import search_audio
 
files = ["ep1.mp3", "ep2.mp3", "ep3.mp3"]
for f in files:
    results = search_audio(f, ["keyword"])

from augent import get_cache_stats, clear_cache, list_cached
 
# View stats
stats = get_cache_stats()
 
# List all cached transcriptions
entries = list_cached()
for e in entries:
    print(f"{e['title']} - {e['duration_formatted']}")
 
# Clear cache
cleared = clear_cache()

from augent import export_matches, export_transcription
 
# Export search results
csv_output = export_matches(matches, format="csv")
srt_output = export_matches(matches, format="srt")
 
# Export full transcription as subtitles
srt = export_transcription(result["segments"], format="srt")

from augent import export_clips
 
clips = export_clips(
    "podcast.mp3",
    matches,
    output_dir="./clips",
    padding=5.0
)

from augent import transcribe_audio_streaming
 
for progress in transcribe_audio_streaming("podcast.mp3"):
    print(f"{progress.progress:.0%} - {progress.message}")