Quick Start Guide

pip install audiopod-client

# Set environment variable
import os
os.environ['AUDIOPOD_API_KEY'] = 'your_api_key_here'

# Or use .env file
# Create .env file with: AUDIOPOD_API_KEY=your_api_key_here
from dotenv import load_dotenv
load_dotenv()

from audiopod import Client

# Initialize client
client = Client()

# Generate speech
result = client.voice.generate_speech(
    voice_id="aura",
    text="Hello world! This is my first AudioPod AI generated voice.",
    language="en",
    audio_format="mp3",
    wait_for_completion=True
)

print(f"Audio generated: {result.output_url}")

# Download the audio file
import requests
audio_response = requests.get(result.output_url)
with open("hello_world.mp3", "wb") as f:
    f.write(audio_response.content)

print("Audio saved as hello_world.mp3")

# Create a voice profile from audio sample
voice_profile = client.voice.create_voice_profile(
    name="My Custom Voice",
    voice_file="path/to/voice_sample.wav",
    description="A custom voice for my project",
    wait_for_completion=True
)

print(f"Voice profile created: {voice_profile.id}")

# Use the new voice for speech generation
cloned_speech = client.voice.generate_speech(
    voice_id=voice_profile.id,
    text="This is my cloned voice speaking!",
    wait_for_completion=True
)

print(f"Cloned speech: {cloned_speech.output_url}")

# Generate music from text prompt
music_job = client.music.generate_music(
    prompt="upbeat electronic dance music with heavy bass",
    duration=120.0,  # 2 minutes
    wait_for_completion=True
)

print(f"Music generated: {music_job.output_url}")

# Generate rap music
rap_job = client.music.generate_rap(
    lyrics="AudioPod AI, the future is here, Making music that's crystal clear",
    style="modern",
    tempo=120,
    wait_for_completion=True
)

print(f"Rap generated: {rap_job.output_url}")

# Transcribe audio file
transcription = client.transcription.transcribe_audio(
    audio_file="path/to/meeting_recording.wav",
    language="en",
    enable_speaker_diarization=True,
    enable_word_timestamps=True,
    wait_for_completion=True
)

print(f"Transcript: {transcription.transcript}")
print(f"Detected language: {transcription.detected_language}")

# Transcribe from URL (YouTube, etc.)
url_transcription = client.transcription.transcribe_url(
    url="https://youtube.com/watch?v=example",
    enable_speaker_diarization=True,
    wait_for_completion=True
)

print(f"URL Transcript: {url_transcription.transcript}")

# Check credit balance
credits = client.credits.get_credit_balance()
print(f"Available credits: {credits.balance}")
print(f"Pay-as-you-go credits: {credits.payg_balance}")
print(f"Total available: {credits.total_available_credits}")

# Get usage history
usage_history = client.credits.get_usage_history()
for usage in usage_history:
    print(f"Used {usage.credits_used} credits for {usage.feature}")

# Translate audio file
translation = client.translation.translate_audio(
    audio_file="path/to/spanish_audio.wav",
    target_language="en",
    source_language="es",
    wait_for_completion=True
)

print(f"Translated audio: {translation.translated_audio_url}")
print(f"Original transcript: {translation.transcript}")
print(f"Translated text: {translation.translated_text}")

# Denoise audio
denoised = client.denoiser.denoise_audio(
    audio_file="path/to/noisy_audio.wav",
    quality_mode="balanced",
    wait_for_completion=True
)

print(f"Denoised audio: {denoised.output_url}")

# Split stems from music
stems = client.stem_extraction.extract_stems(
    audio_file="path/to/song.wav",
    stem_types=["vocals", "drums", "bass", "other"],
    wait_for_completion=True
)

print("Separated stems:")
for stem_type, url in stems.download_urls.items():
    print(f"{stem_type}: {url}")