Lyria 3.5
Music generation model for full-length songs with vocals and structure from text or image prompts
- Context window
- 131.1K tokens in · 65.5K out
BENCHMARKS
Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.
Google's past year
37 release days in the past year, about one every 10 days. The next is expected around Nov 3, 2026. Forecasts ↗
NovDecJanFebMarAprMayJunJulAugSepOctNov
More from the lab
Related article · Sep 4, 2026Create your best tracks yet with Lyria 3.5 in Gemini.Specifications
RELEASE DATEJul 29, 2026
WEIGHTSClosed weights
CONTEXT WINDOW131.1K
MAX OUTPUT65.5K
REASONINGNot listed
TOOL CALLINGNot listed
INPUTStext, image/png, image/jpeg, image/webp, image/heic, image/heif
OUTPUTStext, audio/mp3, audio/wav
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.