infsh login

# Create avatar video from image + audio
infsh app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "https://speech.mp3"
}'

infsh app list --search "omnihuman"
infsh app list --search "lipsync"
infsh app list --search "fabric"

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

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

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

# 1. Generate speech from text
infsh 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
infsh app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://presenter-photo.jpg",
  "audio_url": "<audio-url-from-step-1>"
}'

# 1. Transcribe original video
infsh 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
infsh app run infsh/kokoro-tts --input '{"text": "<translated-text>"}' > new_speech.json

# 4. Lipsync the original video with new audio
infsh app run infsh/latentsync-1-6 --input '{
  "video_url": "https://original-video.mp4",
  "audio_url": "<new-audio-url>"
}'

# Full platform skill (all 150+ apps)
npx skills add inference-sh/skills@agent-tools

# Text-to-speech (generate audio for avatars)
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