Creating a podcast transcript
The OpenAI API Audio endpoint provides access to the different models, which can be used for speech-to-text transcription and translation. In this exercise, you'll create a transcript from a DataFramed podcast episode with OpenAI Developer, Logan Kilpatrick.
If you'd like to hear more from Logan, check out the full ChatGPT and the OpenAI Developer Ecosystem podcast episode.
Latihan ini adalah bagian dari kursus
Multi-Modal Systems with the OpenAI API
Petunjuk latihan
- Open the
openai-audio.mp3file. - Create a transcription request to the Audio endpoint with
audio_file. - Extract and print the transcript text from the
response.
Latihan interaktif praktis
Cobalah latihan ini dengan menyelesaikan kode contoh berikut.
client = OpenAI(api_key="")
# Open the openai-audio.mp3 file
audio_file = ____(____, "rb")
# Create a transcript from the audio file
response = client.audio.transcriptions.____(model="whisper-1", file=____)
# Extract and print the transcript text
print(response.____)