Audio on Google Cloud

from google.api_core.client_options import ClientOptions
from google.cloud.speech_v2 import SpeechClient
from google.cloud.speech_v2.types import cloud_speech

# Initialize client
client = SpeechClient(
    client_options=ClientOptions(api_endpoint="us-speech.googleapis.com")
)

# Configure recognition
config = cloud_speech.RecognitionConfig(
    auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
    model="chirp_3",
    language_codes=["en-US"],
)

# Read audio file
with open("audio.mp3", "rb") as f:
    audio_content = f.read()

# Create request
request = cloud_speech.RecognizeRequest(
    recognizer=f"projects/{PROJECT_ID}/locations/us/recognizers/_",
    config=config,
    content=audio_content,
)

# Get transcription
response = client.recognize(request=request)
for result in response.results:
    print(result.alternatives[0].transcript)

from google.api_core.client_options import ClientOptions
from google.cloud import texttospeech_v1beta1 as texttospeech

# Initialize client
client = texttospeech.TextToSpeechClient(
    client_options=ClientOptions(api_endpoint="texttospeech.googleapis.com")
)

# Configure synthesis
voice = texttospeech.VoiceSelectionParams(
    language_code="en-US",
    name="en-US-Chirp3-HD-F1",
)

audio_config = texttospeech.AudioConfig(
    audio_encoding=texttospeech.AudioEncoding.MP3,
)

# Create request
request = texttospeech.SynthesizeSpeechRequest(
    input=texttospeech.SynthesisInput(text="Hello, world!"),
    voice=voice,
    audio_config=audio_config,
)

# Get audio
response = client.synthesize_speech(request=request)
with open("output.mp3", "wb") as f:
    f.write(response.audio_content)

import base64
import google.auth
import google.auth.transport.requests
import requests

# Get credentials
creds, project = google.auth.default()
auth_req = google.auth.transport.requests.Request()
creds.refresh(auth_req)

# API endpoint
endpoint = f"https://us-central1-aiplatform.googleapis.com/v1/projects/{PROJECT_ID}/locations/us-central1/publishers/google/models/lyria-002:predict"

# Create request
data = {
    "instances": [{
        "prompt": "Smooth, atmospheric jazz with mellow brass",
        "negative_prompt": "fast",
        "sample_count": 1
    }],
    "parameters": {}
}

headers = {
    "Authorization": f"Bearer {creds.token}",
    "Content-Type": "application/json",
}

# Generate music
response = requests.post(endpoint, headers=headers, json=data)
result = response.json()

# Decode audio
audio_bytes = base64.b64decode(result["predictions"][0]["bytesBase64Encoded"])
with open("music.wav", "wb") as f:
    f.write(audio_bytes)