openai-python/examples/audio.py at main · yaohwang/openai-python · GitHub

Repository navigation

History

#!/usr/bin/env rye run python

import time

from pathlib import Path

from openai import OpenAI

# gets OPENAI_API_KEY from your environment variables

openai = OpenAI()

speech_file_path = Path(__file__).parent / "speech.mp3"

def main() -> None:

stream_to_speakers()

# Create text-to-speech audio file

with openai.audio.speech.with_streaming_response.create(

model="tts-1",

voice="alloy",

input="the quick brown fox jumped over the lazy dogs",

) as response:

response.stream_to_file(speech_file_path)

# Create transcription from audio file

transcription = openai.audio.transcriptions.create(

model="whisper-1",

file=speech_file_path,

)

print(transcription.text)

# Create translation from audio file

translation = openai.audio.translations.create(

model="whisper-1",

file=speech_file_path,

)

print(translation.text)

def stream_to_speakers() -> None:

import pyaudio

player_stream = pyaudio.PyAudio().open(format=pyaudio.paInt16, channels=1, rate=24000, output=True)

start_time = time.time()

with openai.audio.speech.with_streaming_response.create(

model="tts-1",

voice="alloy",

response_format="pcm", # similar to WAV, but without a header chunk at the start.

input="""I see skies of blue and clouds of white

The bright blessed days, the dark sacred nights

And I think to myself

What a wonderful world""",

) as response:

print(f"Time to first byte: {int((time.time() - start_time) * 1000)}ms")

for chunk in response.iter_bytes(chunk_size=1024):

player_stream.write(chunk)

print(f"Done in {int((time.time() - start_time) * 1000)}ms.")

if __name__ == "__main__":

main()

openai-python/examples/audio.py at main · yaohwang/openai-python · GitHub

Repository navigation

Expand file tree

Breadcrumbs

audio.py

Latest commit

History

Breadcrumbs

audio.py

File metadata and controls