Out

Chat

disable

Lyria 2

Google's Lyria 2 is an advanced AI model that generates professional-grade, instrumental music from text prompts, offering creators fine-tuned controls.

Free $1 Tokens for New Members

Text to Speech

Javascript

Python

                                        const main = async () => {
  const response = await fetch('https://api.ai.cc/v2/generate/audio', {
    method: 'POST',
    headers: {
      Authorization: 'Bearer ',
      'Content-Type': 'application/json',
    },
    body: JSON.stringify({
      model: 'google/lyria2',
      prompt: 'lo-fi pop hip-hop ambient music',
    }),
  }).then((res) => res.json());

  console.log('Generation:', response);
};

main()

                                        import requests


def main():
    url = "https://api.ai.cc/v2/generate/audio"
    payload = {
        "model": "google/lyria2",
        "prompt": "lo-fi pop hip-hop ambient music",
    }
    headers = {"Authorization": "Bearer ", "Content-Type": "application/json"}

    response = requests.post(url, json=payload, headers=headers)
    print("Generation:", response.json())


if __name__ == "__main__":
    main()

Docs

One API 300+ AI Models

Save 20% on Costs & $1 Free Tokens

Get API Key Explore Models

AI Playground

Test all API models in the sandbox environment before you integrate.

We provide more than 300 models to integrate into your app.

Lyria 2

Product Detail

✨ Discover Lyria 2: Google's Advanced AI Music Generation Model

Google's Lyria 2 is a cutting-edge AI model specifically engineered for high-fidelity music generation. It excels at producing professional-grade, instrumental audio directly from descriptive text prompts, empowering creators to bring their musical visions to life with unprecedented control and quality.

⚙️ Technical Specifications & Performance Metrics

Performance Benchmarks

Lyria 2 is meticulously optimized for professional-grade, text-to-music audio generation, ensuring top-tier output for demanding applications.

🎧 Audio Output: Generates 30 seconds of pristine 48kHz stereo WAV audio per request.
⚡ Generation Speed: Expect audio clips to be typically generated within 10 to 20 seconds, facilitating rapid prototyping and iteration.
💰 API Pricing: Highly competitive at 0.105 $/generation.

Quality and User Feedback

Despite the absence of formal benchmarks, user feedback consistently praises Lyria 2 for its superior audio quality. Many users claim it surpasses existing competitors like Suno and Udio, particularly highlighting its granular creative controls as a crucial advantage for professional musicians and content creators.

▶️ See Lyria 2 in Action

Watch this video to understand how to create compelling music with Lyria 2:

Original Video: Creating music with Lyria 2

🚀 Key Capabilities of Lyria 2

Lyria 2 empowers users with precise and controllable audio outputs, ideal for a wide array of creative and professional applications:

🎵 Text-to-Music Generation: Effortlessly create instrumental music tracks from descriptive text prompts. Specify genre, mood, instrumentation, and tempo to guide the AI.
🎛️ Advanced Creative Controls:
- Supports negative prompting to exclude unwanted elements, ensuring your output is clean and focused.
- Features seed-based generation for reproducible outputs, critical for iterative development.
- Offers advanced settings for tempo (BPM) and key signature, giving musicians granular control.
🌍 Genre Versatility: Lyria 2 covers an extensive range of musical styles, including classical, jazz, pop, electronic, orchestral, and various regional styles, making it incredibly adaptable.

💡 Optimal Use Cases for Lyria 2

Lyria 2 is designed to excel in various professional and creative scenarios:

🎬 Content Creation: Generate bespoke background music and unique scores for digital content, including YouTube Shorts, podcasts, and social media videos.
🎼 Musical Prototyping: Assist musicians in rapidly creating demos, exploring new musical ideas, and refining compositions with precise controls over tempo and key.
🌳 Soundscape Design: Craft immersive ambient audio and diverse sound effects for games, films, or interactive experiences from simple text descriptions.

💻 API Code Samples & Parameters

Integrating Lyria 2 into your applications is straightforward. Here’s a conceptual look at how you might interact with its API for music generation:

Music Generation (Conceptual)


// Example for generating audio.
// This snippet is conceptual and depends on the specific API client/SDK.
// Refer to official documentation for exact syntax.

// audio.createGeneration({
//     model: "google/lyria2",
//     prompt: "An upbeat jazz track with piano, bass, and drums, 120 bpm, in C major.",
//     negative_prompt: "No trumpets or distorted guitars.",
//     seed: 12345
// });

Get Generated Audio (Conceptual)


// Example for fetching generated audio.
// audio.fetchGeneration("generation_id_xyz123");

Key API Parameters

model: string - Specifies the AI model to use (e.g., "google/lyria2").
prompt: string - The descriptive text prompt to guide audio generation.
negative_prompt: string - A description of elements to exclude from the generated audio.
seed: number - An optional seed for deterministic generation. Providing a seed helps reproduce the same audio output given identical prompts and parameters.

⚖️ Comparison with Other Google AI Models

Lyria 2 vs. Google MusicFX/MusicLM: Lyria 2 represents a significant advancement over Google's previous models like MusicFX and MusicLM. It offers more sophisticated controls such as BPM and key signature adjustments, alongside capabilities for lyric-to-song generation.
Lyria 2 vs. Lyria RealTime: It's important to distinguish between these two models. Lyria 2 is primarily designed for generating complete, high-quality audio clips from text prompts. In contrast, Lyria RealTime is a separate model specifically focused on interactive and real-time music creation and performance, offering different functionalities for live applications.

🔗 Seamless API Integration

Lyria 2 is easily accessible via the AI/ML API, enabling developers to integrate its powerful music generation capabilities into their own platforms and applications. For comprehensive details and implementation guidelines, refer to the official documentation:

Access Lyria 2 API Documentation Here

❓ Frequently Asked Questions (FAQ)

Q: What is Lyria 2 primarily used for?
A: Lyria 2 is ideal for generating professional-grade instrumental background music, scores, and sound effects for content creation, musical prototyping, and soundscape design from text prompts.
Q: How does Lyria 2 compare to Google's earlier music AI models?
A: Lyria 2 offers significant improvements over models like MusicFX and MusicLM, providing more advanced controls such as BPM, key signature, and lyric-to-song generation capabilities.
Q: Can I control specific musical elements like tempo or key with Lyria 2?
A: Yes, Lyria 2 features advanced controls including negative prompting, seed-based generation, and specific settings for tempo (BPM) and key signature, giving users granular creative control.
Q: What is the typical generation speed and audio quality of Lyria 2?
A: Lyria 2 typically generates 30 seconds of high-fidelity 48kHz stereo WAV audio within 10 to 20 seconds.
Q: Is Lyria 2 suitable for real-time music performance?
A: No, Lyria 2 is designed for generating complete audio clips. For interactive, real-time music creation and performance, Google offers Lyria RealTime, a separate model.

Learn how you can transformyour company with AICC APIs

Discover how to revolutionize your business with AICC API! Unlock powerfultools to automate processes, enhance decision-making, and personalize customer experiences.

Contact sales

One API
300+ AI Models

Save 20% on Costs

Free $1 Tokens for New Members