●GA — Gemini Omni Flash reached general availability on August 27 as gemini-omni-1.1-flash, the conversational video generation and editing model●EXTEND — You can now continue an existing clip by generating past its end, either through the extend task or straight from a prompt, working around the short duration limit●RESOLUTION — video_config gains a resolution parameter offering 360p, 720p, 1080p, and 4k. The two highest tiers are produced by upscaling, so results vary with the source●DEPRECATION — gemini-omni-flash-preview shuts down on September 30, so any production code still pointing at the preview endpoint needs to move over●TRANSCRIBE — Gemini 3.5 Transcribe and Transcribe Live went GA on August 26 with language detection across 85+ languages, speaker diarization, and word-level timestamps●SHUTDOWN — gemini-robotics-er-1.6-preview retires on August 31, two days from now, with the ER 2 line in public preview since July 30 as the migration path●GA — Gemini Omni Flash reached general availability on August 27 as gemini-omni-1.1-flash, the conversational video generation and editing model●EXTEND — You can now continue an existing clip by generating past its end, either through the extend task or straight from a prompt, working around the short duration limit●RESOLUTION — video_config gains a resolution parameter offering 360p, 720p, 1080p, and 4k. The two highest tiers are produced by upscaling, so results vary with the source●DEPRECATION — gemini-omni-flash-preview shuts down on September 30, so any production code still pointing at the preview endpoint needs to move over●TRANSCRIBE — Gemini 3.5 Transcribe and Transcribe Live went GA on August 26 with language detection across 85+ languages, speaker diarization, and word-level timestamps●SHUTDOWN — gemini-robotics-er-1.6-preview retires on August 31, two days from now, with the ER 2 line in public preview since July 30 as the migration path