Python Audio

from openai import OpenAI

client = OpenAI(api_key="sk-xxx", base_url="https://api.crazyrouter.com/v1")

# Generate speech
response = client.audio.speech.create(
    model="tts-1",
    voice="alloy",
    input="Hello, welcome to the Crazyrouter API service."
)

# Save as MP3 file
response.stream_to_file("output.mp3")
print("Audio saved to output.mp3")

# Use tts-1-hd for higher audio quality
response = client.audio.speech.create(
    model="tts-1-hd-1106",
    voice="nova",
    input="High quality speech synthesis example",
    response_format="opus",  # Supports mp3, opus, aac, flac
    speed=1.0  # 0.25 to 4.0
)

response.stream_to_file("output_hd.opus")

# Whisper speech recognition
audio_file = open("recording.mp3", "rb")

transcript = client.audio.transcriptions.create(
    model="whisper-1",
    file=audio_file,
    language="en"  # Optional, specifying language improves accuracy
)

print(transcript.text)

transcript = client.audio.transcriptions.create(
    model="whisper-1",
    file=open("recording.mp3", "rb"),
    response_format="verbose_json",
    timestamp_granularities=["segment"]
)

for segment in transcript.segments:
    print(f"[{segment['start']:.1f}s - {segment['end']:.1f}s] {segment['text']}")

audio_file = open("foreign_audio.mp3", "rb")

translation = client.audio.translations.create(
    model="whisper-1",
    file=audio_file
)

print(translation.text)  # English output