# Search audio/voice models
modelslab models search --feature audio_gen

# Search by provider
modelslab models search --search "eleven"

# Get model details
modelslab models detail --id eleven_multilingual_v2

import requests
import time

def text_to_speech(text, api_key, voice_id="21m00Tcm4TlvDq8ikWAM", model_id="eleven_multilingual_v2"):
    """Convert text to speech.

    Args:
        text: The text to convert to speech
        api_key: Your ModelsLab API key
        voice_id: ElevenLabs voice ID (see Available Voices below)
        model_id: TTS model to use
    """
    response = requests.post(
        "https://modelslab.com/api/v7/voice/text-to-speech",
        json={
            "key": api_key,
            "prompt": text,             # v7 uses "prompt" not "text"
            "voice_id": voice_id,
            "model_id": model_id
        }
    )

    data = response.json()

    if data["status"] == "success":
        return data["output"][0]
    elif data["status"] == "processing":
        return poll_audio_result(data["id"], api_key)
    else:
        raise Exception(f"Error: {data.get('message', 'Unknown error')}")

# Usage
audio_url = text_to_speech(
    "Hello! Welcome to ModelsLab. This is a test of our text-to-speech API.",
    "your_api_key"
)
print(f"Audio URL: {audio_url}")

def speech_to_text(audio_url, api_key, model_id="scribe_v1"):
    """Transcribe speech from audio to text.

    Args:
        audio_url: URL of audio file (must be publicly accessible)
        model_id: STT model to use
    """
    response = requests.post(
        "https://modelslab.com/api/v7/voice/speech-to-text",
        json={
            "key": api_key,
            "init_audio": audio_url,    # v7 uses "init_audio" not "audio"
            "model_id": model_id
        }
    )

    data = response.json()

    if data["status"] == "success":
        return data["output"][0]
    elif data["status"] == "processing":
        return poll_audio_result(data["id"], api_key)
    else:
        raise Exception(data.get("message"))

# Transcribe audio
result = speech_to_text(
    "https://example.com/speech.mp3",
    "your_api_key"
)
print(f"Transcription: {result}")

def speech_to_speech(audio_url, voice_id, api_key, model_id="eleven_english_sts_v2"):
    """Convert voice characteristics in audio.

    Args:
        audio_url: URL of the source audio
        voice_id: Target ElevenLabs voice ID
        model_id: Voice conversion model
    """
    response = requests.post(
        "https://modelslab.com/api/v7/voice/speech-to-speech",
        json={
            "key": api_key,
            "init_audio": audio_url,
            "voice_id": voice_id,
            "model_id": model_id
        }
    )

    data = response.json()
    if data["status"] == "success":
        return data["output"][0]
    elif data["status"] == "processing":
        return poll_audio_result(data["id"], api_key)

def generate_sound_effect(description, api_key, model_id="eleven_sound_effect"):
    """Generate a sound effect from a text description.

    Args:
        description: What sound to generate
        model_id: Sound effects model
    """
    response = requests.post(
        "https://modelslab.com/api/v7/voice/sound-generation",
        json={
            "key": api_key,
            "prompt": description,
            "model_id": model_id
        }
    )

    data = response.json()
    if data["status"] == "success":
        return data["output"][0]
    elif data["status"] == "processing":
        return poll_audio_result(data["id"], api_key)

# Generate door slam sound
sfx_url = generate_sound_effect(
    "Heavy wooden door slamming shut",
    "your_api_key"
)

def generate_music(prompt, api_key, model_id="music_v1"):
    """Generate music from a text description.

    Args:
        prompt: Description of music style/mood
        model_id: Music generation model
    """
    response = requests.post(
        "https://modelslab.com/api/v7/voice/music-gen",
        json={
            "key": api_key,
            "prompt": prompt,
            "model_id": model_id
        }
    )

    data = response.json()
    if data["status"] == "success":
        return data["output"][0]
    elif data["status"] == "processing":
        return poll_audio_result(data["id"], api_key)

# Generate background music
music_url = generate_music(
    "Upbeat electronic music with a driving beat, perfect for a tech startup video",
    "your_api_key"
)
print(f"Music: {music_url}")

def poll_audio_result(request_id, api_key, timeout=300):
    """Poll for async audio generation results."""
    start_time = time.time()

    while time.time() - start_time < timeout:
        fetch = requests.post(
            f"https://modelslab.com/api/v7/voice/fetch/{request_id}",
            json={"key": api_key}
        )
        result = fetch.json()

        if result["status"] == "success":
            return result["output"][0]
        elif result["status"] == "failed":
            raise Exception(result.get("message", "Generation failed"))

        time.sleep(5)

    raise Exception("Timeout waiting for audio generation")

payload = {
    "key": api_key,
    "prompt": "...",
    "model_id": "eleven_multilingual_v2",
    "webhook": "https://yourserver.com/webhook/audio",
    "track_id": "audio_001"
}

try:
    audio = text_to_speech(text, api_key)
    print(f"Audio generated: {audio}")
except Exception as e:
    print(f"Audio generation failed: {e}")