●LYRIA — Lyria 3.5 entered public preview on September 3. It generates full-length songs rather than loops, with fine-grained control over duration and structure●INPUT — The model ID is lyria-3.5, and it accepts images alongside text. Being able to say make it feel like this photo changes how you approach the prompt●SPEC — Output is 44.1kHz stereo, the input ceiling is 131,072 tokens, and it can write lyrics. Worth carrying those units whenever you quote the numbers●VIDEO — The agentic video understanding released September 1 lets the model walk a timeline itself, pulling transcripts or frames on demand. Up to 88% fewer tokens on long content●QUIET — Nothing new has landed in the API release notes since September 3. A quiet stretch is still worth recording rather than passing over in silence●DICTATION — On the app side, holding the Fn key now dictates into your active window, dropping cleaned-up text straight at the cursor●LYRIA — Lyria 3.5 entered public preview on September 3. It generates full-length songs rather than loops, with fine-grained control over duration and structure●INPUT — The model ID is lyria-3.5, and it accepts images alongside text. Being able to say make it feel like this photo changes how you approach the prompt●SPEC — Output is 44.1kHz stereo, the input ceiling is 131,072 tokens, and it can write lyrics. Worth carrying those units whenever you quote the numbers●VIDEO — The agentic video understanding released September 1 lets the model walk a timeline itself, pulling transcripts or frames on demand. Up to 88% fewer tokens on long content●QUIET — Nothing new has landed in the API release notes since September 3. A quiet stretch is still worth recording rather than passing over in silence●DICTATION — On the app side, holding the Fn key now dictates into your active window, dropping cleaned-up text straight at the cursor