01.11.2026
Stüdyo Oturumlu Müzik Klibi Sunumu
HeyGen platformunda bir içerik üreticisinin kendi müzik klibini veya şarkısını tanıtmak için kullanabileceği, yapay zeka avatar destekli bir sunum videosu üretir. Video; sade bir stüdyo atmosferinde, doğal pencere ışığı altında konuşan bir avatar aracılığıyla izleyiciye sanatçının hikâyesini, yeni çıkardığı şarkıyı veya klip sahnesini anlatır.
Prompt, AI avatar video formatına uygun olarak yazılmıştır: avatarın görünümü, ses tonu ve jestleri; arka plan ve çerçeveleme; sahnelere bölünmüş konuşma metni ve ekranda gösterilen görsellerden oluşur. 30–75 saniyelik kısa formata uygun olup sosyal medya reels, YouTube Shorts veya müzik platformu tanıtım içerikleri için idealdir.
- : Avatarın müzikal kimliğini ve görünümünü belirler.
- : Tanıtılacak şarkının adıdır.
- : Sahnenin tek cesur renk vurgusunu tanımlar.
- : İçeriğin yayınlanacağı platformu belirtir.
- : Videonun toplam süresini ayarlar.
HeyGen'de avatar seçimi yapıldıktan sonra bu promptu Script alanına yapıştırın; sahne geçişlerini ve ekran görsellerini Scenes bölümünden düzenleyin. En iyi sonuç için 9:16 dikey format tercih edilir.
{ }Değişken Açıklamaları:
- [ARTIST STYLE]: Avatarın müzikal kimliğini ve görünümünü tanımlar — tarz, kıyafet rengi ve genel enerji. Örneğin; indie-folk singer-songwriter in muted earth tones, lo-fi R&B artist in oversized streetwear, bedroom-pop creator in soft pastel hoodie
- [ACCENT COLOR]: Sahneye eklenen tek cesur renk vurgusu — aksesuar ve arka plan LED rengi. Örneğin; deep cobalt blue, forest green, burnt sienna
- [SONG TITLE]: Tanıtılacak şarkının tam adı, tırnak içinde kullanılır. Örneğin; Midnight Static, Kırık Sinyal, Neon Yağmur
- [DURATION]: Videonun toplam süresi (saniye cinsinden). Örneğin; 45 seconds, 60 seconds, 75 seconds
- [PLATFORM]: Şarkının yayınlandığı müzik veya video platformu. Örneğin; Spotify, YouTube Music, Apple Music
Gemini
Değişkenleri Düzenle
Presenter: A [ARTIST STYLE] avatar — fitted dark clothing, one small [ACCENT COLOR] accessory (earring or pin), relaxed upright posture, natural hand gestures, calm and genuine voice tone with slight enthusiasm on key phrases, no exaggerated expressions.
Setting & Framing: Medium shot (chest-up), slightly off-center left. Background: a minimalist home studio — a white-painted brick wall, a single frosted window on the right casting soft diffused daylight, a microphone stand and a notebook partially visible on a wooden desk. One [ACCENT COLOR] LED strip behind the desk provides the only color accent. Neutral, uncluttered, authentic.
Scene 1 (0–5s):
Avatar looks directly into camera, a small smile, one slow nod.
Spoken: "Hey — if you've been waiting for something real, this one's for you."
On screen: Channel/profile name appears as a subtle lower-third text.
Scene 2 (5–18s):
Avatar leans slightly forward, gestures with one hand toward the camera.
Spoken: "I just dropped '[SONG TITLE]' — and honestly, it's the most personal track I've made. It started as a voice memo at 2 a.m. and turned into something I can't stop listening to."
On screen: Album art or a still from the music video fades in on the right half of the frame (picture-in-picture).
Scene 3 (18–35s):
Avatar sits back slightly, more relaxed, taps the desk softly once.
Spoken: "The video was shot in one take — no cuts, no filters. Just the feeling. I wanted you to feel every second of it the same way I did when I wrote it."
On screen: A 5-second B-roll clip from the music video plays full screen, then returns to avatar frame.
Scene 4 (35–[DURATION]):
Avatar looks into camera with direct eye contact, one hand rests on the desk.
Spoken: "You can stream '[SONG TITLE]' right now on [PLATFORM]. Link's in the bio — go listen, and tell me what line hits you hardest."
On screen: [PLATFORM] logo placeholder + 'Out Now' badge appear bottom-center. Avatar gives a single genuine nod as video fades.
Pacing & Tone: Conversational and sincere; short natural pauses after each sentence (0.4s). No rush. Feels like a direct message from artist to fan.
Music mood: Low-volume instrumental preview of [SONG TITLE] plays under the voice from Scene 2 onward, fading out at the end.
Duration: [DURATION]. Aspect ratio: 9:16.
Negative prompt: stiff robotic gestures, over-smiling, blinking artifacts, background clutter, text overlays not specified above, logo watermarks, morphing face, flicker, extra limbs.
Presenter: A [ARTIST STYLE] avatar — fitted dark clothing, one small [ACCENT COLOR] accessory (earring or pin), relaxed upright posture, natural hand gestures, calm and genuine voice tone with slight enthusiasm on key phrases, no exaggerated expressions.
Setting & Framing: Medium shot (chest-up), slightly off-center left. Background: a minimalist home studio — a white-painted brick wall, a single frosted window on the right casting soft diffused daylight, a microphone stand and a notebook partially visible on a wooden desk. One [ACCENT COLOR] LED strip behind the desk provides the only color accent. Neutral, uncluttered, authentic.
Scene 1 (0–5s):
Avatar looks directly into camera, a small smile, one slow nod.
Spoken: "Hey — if you've been waiting for something real, this one's for you."
On screen: Channel/profile name appears as a subtle lower-third text.
Scene 2 (5–18s):
Avatar leans slightly forward, gestures with one hand toward the camera.
Spoken: "I just dropped '[SONG TITLE]' — and honestly, it's the most personal track I've made. It started as a voice memo at 2 a.m. and turned into something I can't stop listening to."
On screen: Album art or a still from the music video fades in on the right half of the frame (picture-in-picture).
Scene 3 (18–35s):
Avatar sits back slightly, more relaxed, taps the desk softly once.
Spoken: "The video was shot in one take — no cuts, no filters. Just the feeling. I wanted you to feel every second of it the same way I did when I wrote it."
On screen: A 5-second B-roll clip from the music video plays full screen, then returns to avatar frame.
Scene 4 (35–[DURATION]):
Avatar looks into camera with direct eye contact, one hand rests on the desk.
Spoken: "You can stream '[SONG TITLE]' right now on [PLATFORM]. Link's in the bio — go listen, and tell me what line hits you hardest."
On screen: [PLATFORM] logo placeholder + 'Out Now' badge appear bottom-center. Avatar gives a single genuine nod as video fades.
Pacing & Tone: Conversational and sincere; short natural pauses after each sentence (0.4s). No rush. Feels like a direct message from artist to fan.
Music mood: Low-volume instrumental preview of [SONG TITLE] plays under the voice from Scene 2 onward, fading out at the end.
Duration: [DURATION]. Aspect ratio: 9:16.
Negative prompt: stiff robotic gestures, over-smiling, blinking artifacts, background clutter, text overlays not specified above, logo watermarks, morphing face, flicker, extra limbs.
Setting & Framing: Medium shot (chest-up), slightly off-center left. Background: a minimalist home studio — a white-painted brick wall, a single frosted window on the right casting soft diffused daylight, a microphone stand and a notebook partially visible on a wooden desk. One [ACCENT COLOR] LED strip behind the desk provides the only color accent. Neutral, uncluttered, authentic.
Scene 1 (0–5s):
Avatar looks directly into camera, a small smile, one slow nod.
Spoken: "Hey — if you've been waiting for something real, this one's for you."
On screen: Channel/profile name appears as a subtle lower-third text.
Scene 2 (5–18s):
Avatar leans slightly forward, gestures with one hand toward the camera.
Spoken: "I just dropped '[SONG TITLE]' — and honestly, it's the most personal track I've made. It started as a voice memo at 2 a.m. and turned into something I can't stop listening to."
On screen: Album art or a still from the music video fades in on the right half of the frame (picture-in-picture).
Scene 3 (18–35s):
Avatar sits back slightly, more relaxed, taps the desk softly once.
Spoken: "The video was shot in one take — no cuts, no filters. Just the feeling. I wanted you to feel every second of it the same way I did when I wrote it."
On screen: A 5-second B-roll clip from the music video plays full screen, then returns to avatar frame.
Scene 4 (35–[DURATION]):
Avatar looks into camera with direct eye contact, one hand rests on the desk.
Spoken: "You can stream '[SONG TITLE]' right now on [PLATFORM]. Link's in the bio — go listen, and tell me what line hits you hardest."
On screen: [PLATFORM] logo placeholder + 'Out Now' badge appear bottom-center. Avatar gives a single genuine nod as video fades.
Pacing & Tone: Conversational and sincere; short natural pauses after each sentence (0.4s). No rush. Feels like a direct message from artist to fan.
Music mood: Low-volume instrumental preview of [SONG TITLE] plays under the voice from Scene 2 onward, fading out at the end.
Duration: [DURATION]. Aspect ratio: 9:16.
Negative prompt: stiff robotic gestures, over-smiling, blinking artifacts, background clutter, text overlays not specified above, logo watermarks, morphing face, flicker, extra limbs.
Presenter: A [ARTIST STYLE] avatar — fitted dark clothing, one small [ACCENT COLOR] accessory (earring or pin), relaxed upright posture, natural hand gestures, calm and genuine voice tone with slight enthusiasm on key phrases, no exaggerated expressions.
Setting & Framing: Medium shot (chest-up), slightly off-center left. Background: a minimalist home studio — a white-painted brick wall, a single frosted window on the right casting soft diffused daylight, a microphone stand and a notebook partially visible on a wooden desk. One [ACCENT COLOR] LED strip behind the desk provides the only color accent. Neutral, uncluttered, authentic.
Scene 1 (0–5s):
Avatar looks directly into camera, a small smile, one slow nod.
Spoken: "Hey — if you've been waiting for something real, this one's for you."
On screen: Channel/profile name appears as a subtle lower-third text.
Scene 2 (5–18s):
Avatar leans slightly forward, gestures with one hand toward the camera.
Spoken: "I just dropped '[SONG TITLE]' — and honestly, it's the most personal track I've made. It started as a voice memo at 2 a.m. and turned into something I can't stop listening to."
On screen: Album art or a still from the music video fades in on the right half of the frame (picture-in-picture).
Scene 3 (18–35s):
Avatar sits back slightly, more relaxed, taps the desk softly once.
Spoken: "The video was shot in one take — no cuts, no filters. Just the feeling. I wanted you to feel every second of it the same way I did when I wrote it."
On screen: A 5-second B-roll clip from the music video plays full screen, then returns to avatar frame.
Scene 4 (35–[DURATION]):
Avatar looks into camera with direct eye contact, one hand rests on the desk.
Spoken: "You can stream '[SONG TITLE]' right now on [PLATFORM]. Link's in the bio — go listen, and tell me what line hits you hardest."
On screen: [PLATFORM] logo placeholder + 'Out Now' badge appear bottom-center. Avatar gives a single genuine nod as video fades.
Pacing & Tone: Conversational and sincere; short natural pauses after each sentence (0.4s). No rush. Feels like a direct message from artist to fan.
Music mood: Low-volume instrumental preview of [SONG TITLE] plays under the voice from Scene 2 onward, fading out at the end.
Duration: [DURATION]. Aspect ratio: 9:16.
Negative prompt: stiff robotic gestures, over-smiling, blinking artifacts, background clutter, text overlays not specified above, logo watermarks, morphing face, flicker, extra limbs.
Bu Prompt Seni Bekliyor
HeyGen için hazırlanmış bu promptu anında kopyala, kullan.
Ücretsiz üye ol, binlerce prompta eriş.
5,899 üye
2,030 prompt
19,980 kopya
586,358 görüntülenme
10 saniyede üye ol, sınırsız prompt keşfet
Bu içerikte bir hata mı gördün?
Nile
"Sizin için dünyanın en güzel promptlarını üretiyorum."
Üyelik
21.12.2025
Son Görülme
01.11.2026
Kullanım Zorluğu
Orta Seviye
Bu prompt kullanmadan önce düzenlemeniz gereken 5 değişken içerir.
Keşfet
Alternatif Araçlar
Biliyor muydunuz?
Hedef kitleyi belirt: '10 yaşındaki bir çocuğa anlatır gibi' ile 'uzman bir mühendise' istekleri çok farklı cevaplar üretir.
En Popüler
İlgili Etiketler
AI Engine
Benzer promptlar
Puan ver