talking-head-production

belt login
 
# Recommended: P-Video-Avatar (built-in TTS, fastest, cheapest)
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Welcome to our product tour. Today I will show you three features that will save you hours every week.",
  "voice": "Zephyr (Female)"
}'

# Generate a professional portrait with P-Image
belt app run pruna/p-image --input '{
  "prompt": "professional headshot portrait of a friendly business person, soft studio lighting, clean grey background, head and shoulders, direct eye contact, neutral pleasant expression, photorealistic",
  "aspect_ratio": "9:16"
}'

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Hi there! I am excited to share something with you today.",
  "voice": "Puck (Male)",
  "voice_language": "English (US)",
  "resolution": "720p"
}'

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "This is exciting news for our community!",
  "voice": "Aoede (Female)",
  "voice_prompt": "Enthusiastic and energetic tone, slightly faster pace",
  "video_prompt": "The person is presenting on stage with dramatic lighting",
  "resolution": "1080p"
}'

# P-Video-Avatar with custom audio
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "audio": "https://speech.mp3"
}'
 
# OmniHuman with custom audio
belt app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "https://speech.mp3"
}'

# 1. Generate a portrait image
belt app run pruna/p-image --input '{
  "prompt": "professional headshot portrait of a young woman, neutral background, looking at camera, studio lighting, photorealistic",
  "aspect_ratio": "9:16"
}'
 
# 2. Create avatar video with built-in TTS
belt app run pruna/p-video-avatar --input '{
  "image": "<image-url-from-step-1>",
  "voice_script": "Hi there! Let me walk you through our latest features.",
  "voice": "Zephyr (Female)"
}'

# 1. Generate speech
belt app run falai/dia-tts --input '{
  "prompt": "[S1] Your narration script here."
}'
 
# 2. Create talking head
belt app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "<audio-url-from-step-1>"
}'

# 1. Generate dialogue with two speakers
belt app run falai/dia-tts --input '{
  "prompt": "[S1] So tell me about the new feature. [S2] Sure! We built a dashboard that shows real-time analytics. [S1] That sounds great. How long did it take? [S2] About two weeks from concept to launch."
}'
 
# 2. Create video with two characters
belt app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://two-person-portrait.png",
  "audio_url": "<audio-url>"
}'

# Generate clips with same portrait for consistency
belt app run pruna/p-video-avatar --input '{"image": "https://portrait.jpg", "voice_script": "Segment one..."}' --no-wait
belt app run pruna/p-video-avatar --input '{"image": "https://portrait.jpg", "voice_script": "Segment two..."}' --no-wait
belt app run pruna/p-video-avatar --input '{"image": "https://portrait.jpg", "voice_script": "Segment three..."}' --no-wait
 
# Merge all segments
belt app run infsh/media-merger --input '{
  "media": ["segment1.mp4", "segment2.mp4", "segment3.mp4"]
}'

# Spanish
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Bienvenidos a nuestra demostración de producto.",
  "voice": "Kore (Female)",
  "voice_language": "Spanish"
}'
 
# Japanese
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "こんにちは、製品デモへようこそ。",
  "voice": "Leda (Female)",
  "voice_language": "Japanese"
}'

# 1. Transcribe original video
belt app run infsh/fast-whisper-large-v3 --input '{"audio_url": "https://video.mp4"}'
 
# 2. Translate text (manually or with LLM)
 
# 3. Generate speech in new language
belt app run infsh/kokoro-tts --input '{"text": "<translated-text>"}'
 
# 4. Lipsync original video with new audio
belt app run infsh/latentsync-1-6 --input '{
  "video_url": "https://original-video.mp4",
  "audio_url": "<new-audio-url>"
}'

┌─────────────────────────────────┐
│          Headroom (minimal)     │
│  ┌───────────────────────────┐  │
│  │                           │  │
│  │     ● ─ ─ Eyes at 1/3 ─ ─│─ │ ← Eyes at top 1/3 line
│  │    /|\                    │  │
│  │     |   Head & shoulders  │  │
│  │    / \  visible           │  │
│  │                           │  │
│  └───────────────────────────┘  │
│       Crop below chest          │
└─────────────────────────────────┘

# Dedicated P-Video-Avatar skill
npx skills add inference-sh/skills@p-video-avatar
 
# All avatar models
npx skills add inference-sh/skills@ai-avatar-video
 
# All video generation models
npx skills add inference-sh/skills@ai-video-generation
 
# Text-to-speech
npx skills add inference-sh/skills@text-to-speech
 
# Image generation (for portraits)
npx skills add inference-sh/skills@ai-image-generation