Identity
- Status
- active
- Developer ID
lyria-3.5- Released
- Jul 29, 2026
- Version
- Lyria 3.5
- License
- Unknown
Google DeepMindLyria 3.5
Lyria 3.5 is Google DeepMind's music generation model for high-quality tracks with improved musicality, lyrics, and vocals.
- Token context
- 1,049K tokens
- Inputs
- Text, Image
- Outputs
- Text, Audio
- Released
- Jul 29, 2026
Providers & Pricing
2 current hosted offerings
No Directly Sourced Provider Price Yet
API pricing is provider-specific and stays unknown until a serving provider publishes an exact offering for this model version.
At a Glance
Model Facts
Capacity
- Token context
- 1,049K tokens
- Maximum output
- 66K tokens
- Total parameters
- Unknown
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text, Image
- Outputs
- Text, Audio
- API available
- Yes
- Open weights
- No
- Self-hostable
- No
- Reasoning
- No
- Vision
- Yes
- Tool calling
- No
- Capabilities
- generation, image-to-music, lyrics, music-generation, synthid, vocals
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliaseslyria-3.5, Lyria 3.5
Explicit Unknowns
- Tokenizer
- Knowledge cutoff
- Provider pricing
Primary Evidence
Sources and Observation Date
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Lyria 3.5Google DeepMind | vs |  Muse Spark 1.1Meta | cross-developer peersaudio, image, text |
Lyria 3.5Google DeepMind | vs |  Phi-4 Multimodal InstructMicrosoft | cross-developer peersaudio, image, text |
Lyria 3.5Google DeepMind | vs |  MiniMax Music3MiniMax | cross-developer peersaudio |
Lyria 3.5Google DeepMind | vs |  Stable Audio 3 MediumStability AI | cross-developer peersaudio |
Lyria 3.5Google DeepMind | vs |  InklingThinking Machines Lab | cross-developer peersaudio, image, text |
Questions
Lyria 3.5 FAQs
What is Lyria 3.5?+
Lyria 3.5 is Google DeepMind's music generation model for high-quality tracks with improved musicality, lyrics, and vocals. It is developed by Google DeepMind and its current sourced lifecycle status is active.
What inputs and outputs does Lyria 3.5 support?+
Lyria 3.5's current record lists Text and Image as input and Text and Audio as output.
How much context does Lyria 3.5 support?+
The current record lists a 1,049K-token context window and a maximum output of 66K tokens.
Is Lyria 3.5 available through an API?+
Lyria 3.5 is marked as API-available. The directly sourced provider records currently include Google AI and Google Gemini.
How large is Lyria 3.5?+
The current record lists an unknown total parameter count and an unknown active parameter count. Its architecture is latent diffusion over temporal audio latents.
What capabilities and tasks does Lyria 3.5 support?+
Lyria 3.5's recorded capabilities are generation, image-to-music, lyrics, music-generation, synthid, and vocals. Its supported tasks are audio, image-to-audio, music-generation, and text-to-audio.
How much does Lyria 3.5 cost through an API?+
No directly sourced token price is currently attached to Lyria 3.5. Missing prices remain unknown rather than being inferred from another model or provider.
Can Lyria 3.5 be self-hosted?+
Lyria 3.5 is not marked as an open-weight model. Self-hosting is marked as unsupported, with no license recorded.
Does Lyria 3.5 have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are lyria-3.5 and Lyria 3.5.
Which models can Lyria 3.5 be compared with?+
The current compatible peer set includes Muse Spark 1.1, Phi-4 Multimodal Instruct, MiniMax Music3, Stable Audio 3 Medium, and Inkling. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →