أوصاف فيديو بالذكاء الاصطناعي: أقوى قهوة ورد ساخر من النادل

Create a 15 second dialogue driven cinematic comedy scene in a modern coffee shop. Natural acting, expressive reactions, accurate lip sync, clear dialogue, no overlapping speech. Characters: A: Male, late 20s, serious office worker. B: Female barista, late 20s, calm with dry humor. C: Male customer waiting behind A. 0–4s: A walks to the counter, exhausted but serious. A:“I need the strongest coffee you have. I haven’t slept in two days.” B calmly places a tiny espresso cup in front of him. 4–8s: A looks at the tiny cup, confused. A: “That’s it?” B keeps a completely straight face. 8–12s: B: “No. The hospital is next door.” Brief awkward silence. A slowly looks at her in disbelief. 12–15s: C, who heard everything, immediately puts his coffee back on the counter. C:“I’ll just have water.” B casually nods. A looks directly at the camera, completely defeated. Cut to black. Camera: Medium two shot for A and B, quick close up of the tiny espresso, reaction close up after the hospital line, then reveal C for the final punchline. Bright cinematic café lighting, realistic movement, subtle handheld camera, shallow depth of field, fast natural comedy timing. Keep all characters consistent. Each character speaks only their assigned line. Do not change dialogue or speaker order.