Home › Audio Models › google/lyria-2

google/lyria-2 - AI Audio Models Tool

Overview

Lyria 2 is an AI music generation model by Google that produces professional-grade 48kHz stereo audio from text prompts. It supports multiple genres and implements SynthID watermarking, making outputs suitable for direct project integration.

Key Features

  • Generates professional-grade 48kHz stereo audio from text prompts
  • Supports multiple musical genres
  • Implements SynthID audio watermarking for provenance
  • Suitable for direct integration into projects
  • Hosted on Replicate for model access

Ideal Use Cases

  • Producing original music tracks for media projects
  • Rapidly prototyping musical ideas from text prompts
  • Creating soundtracks for games, films, or ads
  • Generating demo audio for apps and integrations
  • Distributing watermark-protected audio with provenance

Getting Started

  • Open the model page on Replicate: https://replicate.com/google/lyria-2
  • Read usage instructions and examples on the model page
  • Enter a text-based prompt describing the desired music
  • Run generation and download the produced 48kHz stereo audio
  • Verify SynthID watermarking if provenance is required

Pricing

Pricing not disclosed on the model page; consult Replicate or Google for access and pricing details.

Limitations

  • Pricing and access details are not provided in the source
  • No additional metadata or tags were supplied in the provided information

Key Information

  • Category: Audio Models
  • Type: AI Audio Models Tool
Visit Official Website

Related Tools

OpenVoice

OpenVoice is a versatile instant voice cloning framework that allows users to generate speech in multiple languages using only a short audio clip from a reference speaker. The tool provides granular control over voice styles, such as emotion, accent, rhythm, pauses, and intonation, and supports zero-shot cross-lingual voice cloning, enabling users to clone voices across different languages without needing training data for those languages.
WhisperX

WhisperX is an Automatic Speech Recognition (ASR) tool that provides fast and accurate transcriptions with word-level timestamps and speaker diarization features, enhancing the capabilities of OpenAI's Whisper model.
Parler-TTS

A text-to-speech inference and training library for generating high-fidelity speech from text, offering an open-source solution for TTS applications.
SpeechBrain

An all-in-one open-source conversational AI toolkit based on PyTorch offering speech recognition, text-to-speech, speaker recognition, and more.
Whisper Large

A robust speech recognition model based on a Transformer architecture that supports multilingual transcription, speech translation, and language identification.
Retrieval-based Voice Conversion WebUI

An open-source web UI that enables voice conversion using retrieval-based methods, offering configurable options and support for different models.