ai-avatar-video

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Welcome to our product walkthrough. Today I will show you three key features.",
  "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!",
  "voice": "Aoede (Female)",
  "voice_prompt": "Enthusiastic and energetic tone",
  "video_prompt": "The person is presenting on stage with dramatic lighting",
  "resolution": "1080p"
}'

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "audio": "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)"
}'

belt app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "https://speech.mp3"
}'

belt app run falai/fabric-1-0 --input '{
  "image_url": "https://face.jpg",
  "audio_url": "https://audio.mp3"
}'

belt app run falai/pixverse-lipsync --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "https://speech.mp3"
}'

# 1. Generate speech — Inworld TTS-2 for expressive character voices
belt app run inworld/text-to-speech-2 --input '{
  "text": "[friendly] Welcome to our product demo! [excited] Let me show you three features that will change how you work.",
  "voice_id": "Sarah",
  "delivery_mode": "CREATIVE"
}' > speech.json
 
# 2. Create avatar video with the speech
belt app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://presenter-photo.jpg",
  "audio_url": "<audio-url-from-step-1>"
}'

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

# 1. Generate a relatable UGC-style portrait
belt app run pruna/p-image --input '{
  "prompt": "casual selfie-style photo of a young woman in a cozy room, natural lighting, looking at camera, warm smile, authentic feel",
  "aspect_ratio": "9:16"
}'
 
# 2. Create UGC avatar video with built-in TTS
belt app run pruna/p-video-avatar --input '{
  "image": "<image-url-from-step-1>",
  "voice_script": "Okay so I just tried this product and honestly? It is a game changer. I was not expecting to love it this much but here we are!",
  "voice": "Zephyr (Female)",
  "voice_prompt": "Excited, casual, authentic tone like talking to a friend",
  "video_prompt": "The person is talking casually to camera in their room, natural gestures",
  "resolution": "1080p"
}'

# Generate 3 different presenters
for voice in "Zephyr (Female)" "Puck (Male)" "Aoede (Female)"; do
  belt app run pruna/p-video-avatar --input "{
    \"image\": \"https://portrait.jpg\",
    \"voice_script\": \"This changed my morning routine completely. Five minutes and I am done.\",
    \"voice\": \"$voice\",
    \"voice_prompt\": \"Casual, authentic, like a real testimonial\",
    \"video_prompt\": \"Person talking to camera in a bright kitchen\",
    \"resolution\": \"1080p\"
  }"
done

# Dedicated P-Video-Avatar skill
npx skills add inference-sh/skills@p-video-avatar
 
# Full platform skill (all apps)
npx skills add inference-sh/skills@infsh-cli
 
# Text-to-speech (generate audio for non-TTS avatar models)
npx skills add inference-sh/skills@text-to-speech
 
# Speech-to-text (transcribe for dubbing)
npx skills add inference-sh/skills@speech-to-text
 
# Video generation
npx skills add inference-sh/skills@ai-video-generation
 
# Image generation (create avatar images)
npx skills add inference-sh/skills@ai-image-generation