belt login

# Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS)
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Hello, welcome to our product demo!",
  "voice": "Zephyr (Female)"
}'

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 from text
belt app run infsh/kokoro-tts --input '{
  "prompt": "Welcome to our product demo. Today I will show you..."
}' > 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>"
}'

# Dedicated P-Video-Avatar skill
npx skills add inference-sh/skills@p-video-avatar

# Full platform skill (all 250+ 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