Agent Mag
SUBSCRIBE
Lyria 3 Pro Preview
All models
GoogleGoogleGoogleFreeReleased 2026-03-30

Lyria 3 Pro Preview

1.0M contextFreeFree

Lyria 3 Pro Preview is part of Google's Lyria 3 family of music generation models, accessible via the Gemini API. It specializes in generating high-quality, 48kHz stereo audio from text or image prompts, with capabilities for structural coherence, including vocals, timed lyrics, and full instrumental arrangements. The Pro version can produce full-length songs with verses, choruses, and bridges, making it suitable for comprehensive music creation tasks.

What is Lyria 3 Pro Preview?

Lyria 3 Pro Preview is an AI model from Google that Agent Mag tracks for pricing, context window, modalities, benchmarks, and API compatibility. Builders can use this page to compare Lyria 3 Pro Preview against other models for agent workflows and production deployments.

Model ID

Lyria 3 Pro Preview is part of Google's Lyria 3 family of music generation models, accessible via the Gemini API. It specializes in generating high-quality, 48kHz stereo audio from text or image prompts, with capabilities for structural coherence, including vocals, timed lyrics, and full instrumental arrangements. The Pro version can produce full-length songs with verses, choruses, and bridges, making it suitable for comprehensive music creation tasks.

Architecture & Specifications
Tokenizer
Other
License
Proprietary
Released
2026-03-30
Modalities
Input
textimage
Output
textaudio
Supported Parameters
max_tokensresponse_formatseedtemperaturetop_p
Strengths
  • Generates high-quality 48kHz stereo audio
  • Supports text and image prompts for music creation
  • Produces structurally coherent songs with vocals and timed lyrics
  • Capable of generating full-length songs with verses, choruses, and bridges
Limitations
  • No information on training data or parameter count
  • Limited details on customization options for generated music
Recommended Use Cases
Music generation from text prompts
Creating full-length songs with instrumental arrangements
Generating audio for multimedia projects
Producing songs with timed lyrics and vocals

More from Google

Gemma 4 26B A4B
262K ctx$0.060/M

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Gemma 4 31B (free)
262K ctxFree

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Gemma 4 31B
262K ctx$0.130/M

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

Gemma 4 26B A4B (free)
262K ctxFree

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — delivering near-31B quality at...

Related content

Browse the AI models directory

Compare pricing, local installs, context windows, and modality filters across the full model catalog.

Explore AI agent tools

Find frameworks, SDKs, and infrastructure tools that pair with this model in production workflows.

Read Agent Mag model and agent articles

See Agent Mag coverage of model benchmarks, agent frameworks, and deployment patterns.

Data enriched Apr 24, 2026. Pricing from OpenRouter API.