Python Speech-to-Text

from openai import OpenAI client = OpenAI( base_url="https://api.digislash.com/v1", api_key=key ) # Basic transcription audio_file = open("/path/to/file/audio.mp3", "rb") transcription = client.audio.transcriptions.create( model="whisper-1", file=audio_file ) print(transcription.text) # Specify output format transcription = client.audio.transcriptions.create( model="whisper-1", file=audio_file, response_format="text" )

from openai import OpenAI client = OpenAI( base_url="https://api.digislash.com/v1", api_key=key ) audio_file = open("/path/to/file/german.mp3", "rb") translation = client.audio.translations.create( model="whisper-1", file=audio_file ) print(translation.text)

from openai import OpenAI client = OpenAI( base_url="https://api.digislash.com/v1", api_key=key ) audio_file = open("speech.mp3", "rb") transcript = client.audio.transcriptions.create( file=audio_file, model="whisper-1", response_format="verbose_json", timestamp_granularities=["word"] ) print(transcript.words)

from pydub import AudioSegment song = AudioSegment.from_mp3("good_morning.mp3") # Split into 10-minute chunks ten_minutes = 10 * 60 * 1000 first_10_minutes = song[:ten_minutes] first_10_minutes.export("good_morning_10.mp3", format="mp3")