Model Metadata
- v2 only
- Yes
- type
- audio
- name
- Lyria 3.5
- description
- Music generation model for full-length songs with vocals and structure from text or image prompts
- family
- lyria
- open weights
- No
- release date
- 2026-09-03
- modalities
- input: text, image/png, image/jpeg, image/webp, image/heic, image/heif; output: text, audio/mp3, audio/wav
- capabilities
- tools: supported: No; reasoning: supported: No; temperature: Yes; top_p: Yes; top_k: Yes
- limit
- context: 131,072; output: 65,536
Provider Variants 1
Google lyria-3.5
Context 1,048,576 · Output 65,536
- type
- audio
- name
- Lyria 3.5
- description
- Music generation model for full-length songs with vocals and structure from text or image prompts
- family
- lyria
- open weights
- No
- release date
- 2026-09-03
- modalities
- input: text, image/png, image/jpeg, image/webp, image/heic, image/heif; output: text, audio/mp3, audio/wav
- capabilities
- tools: supported: No; reasoning: supported: No; cache: No; structured_output: No; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 1,048,576; output: 65,536
- id
- lyria-3.5
- canonical id
- google/lyria-3.5
- last updated
- 2026-09-03
- api
- generate-content: base_url: https://generativelanguage.googleapis.com/v1beta; sdk: aisdk: @ai-sdk/google; opencodeai: @opencode/ai/providers/google; interactions: base_url: https://generativelanguage.googleapis.com/v1beta; sdk: aisdk: @ai-sdk/google