GEMINI LABJP
DEPRECATION — The two image preview models shut down today, June 25; automations using them must migrate immediatelyGA — In their place, gemini-3.1-flash-image and gemini-3-pro-image are now the generally available native image modelsMEDIA — Video-to-image generation arrives: pass a video as context to create high-quality thumbnails (3.1 flash image only)AUDIO — Gemini 3.1 Flash TTS preview lands: a low-cost, expressive, steerable text-to-speech modelMODEL — Gemini 3.5 Flash is GA, beating 3.1 Pro on nearly every benchmark while running about 4x fasterSEARCH — File Search now supports multimodal search, embedding and searching images natively via gemini-embedding-2DEPRECATION — The two image preview models shut down today, June 25; automations using them must migrate immediatelyGA — In their place, gemini-3.1-flash-image and gemini-3-pro-image are now the generally available native image modelsMEDIA — Video-to-image generation arrives: pass a video as context to create high-quality thumbnails (3.1 flash image only)AUDIO — Gemini 3.1 Flash TTS preview lands: a low-cost, expressive, steerable text-to-speech modelMODEL — Gemini 3.5 Flash is GA, beating 3.1 Pro on nearly every benchmark while running about 4x fasterSEARCH — File Search now supports multimodal search, embedding and searching images natively via gemini-embedding-2
TAG

No articles tagged "音声化"

There are no articles matching this tag right now. Browse a category or popular tag below.

BROWSE BY CATEGORY

Gemini BasicsGemini DevGemini APIGemini AdvancedWorkspaceUpdates

POPULAR TAGS

gemini-api (248)Gemini API (146)production (119)python (93)gemini (88)troubleshooting (81)Gemini (69)automation (41)multimodal (39)indie-dev (37)Python (36)Production (29)