ai-voice-cloning

belt login
 
# Generate speech
belt app run infsh/kokoro-tts --input '{
  "prompt": "Hello! This is an AI-generated voice that sounds natural and engaging.",
  "voice": "af_sarah"
}'

# Expressive character voice with emotion steering
belt app run inworld/text-to-speech-2 --input '{
  "text": "[excited] Oh wow, you actually found the ancient artifact! [gasp] I cannot believe it... [whisper] We need to keep this between us.",
  "voice_id": "Sarah",
  "delivery_mode": "CREATIVE"
}'
 
# Calm narrator with stable delivery
belt app run inworld/text-to-speech-2 --input '{
  "text": "The sun set behind the mountains, casting long shadows across the valley. A new chapter was about to begin.",
  "voice_id": "Sarah",
  "delivery_mode": "STABLE"
}'

# Ultra-fast response for chatbots & game NPCs (~120ms)
belt app run inworld/text-to-speech-1-5-mini --input '{
  "text": "Welcome, traveler. What brings you to our village?",
  "voice_id": "Clive",
  "speaking_rate": 0.9
}'

belt app run infsh/kokoro-tts --input '{
  "prompt": "Welcome to our quarterly earnings call. Today we will discuss the financial performance and strategic initiatives for the past quarter.",
  "voice": "am_michael",
  "speed": 1.0
}'

belt app run infsh/dia-tts --input '{
  "text": "Hey, so I was thinking about that project we discussed. What if we tried a different approach?",
  "voice": "conversational"
}'

belt app run infsh/kokoro-tts --input '{
  "prompt": "Chapter One. The morning mist hung low over the valley as Sarah made her way down the winding path. She had been walking for hours.",
  "voice": "bf_emma",
  "speed": 0.9
}'

belt app run infsh/kokoro-tts --input '{
  "prompt": "Introducing the next generation of productivity. Work smarter, not harder.",
  "voice": "af_nicole",
  "speed": 1.1
}'

belt app run infsh/kokoro-tts --input '{
  "prompt": "Welcome back to Tech Talk! Im your host, and today we are diving deep into the world of artificial intelligence.",
  "voice": "am_adam"
}'

# Generate dialogue between two speakers
# Speaker 1
belt app run infsh/kokoro-tts --input '{
  "prompt": "Have you seen the latest AI developments? Its incredible how fast things are moving.",
  "voice": "am_michael"
}' > speaker1.json
 
# Speaker 2
belt app run infsh/kokoro-tts --input '{
  "prompt": "I know, right? Just last week I tried that new image generator and was blown away.",
  "voice": "af_sarah"
}' > speaker2.json
 
# Merge conversation
belt app run infsh/media-merger --input '{
  "audio_files": ["<speaker1-url>", "<speaker2-url>"],
  "crossfade_ms": 300
}'

# Process long text in chunks
TEXT="Your very long text here..."
 
# Split and generate
# Chunk 1
belt app run infsh/kokoro-tts --input '{
  "prompt": "<chunk-1>",
  "voice": "bf_emma"
}' > chunk1.json
 
# Chunk 2
belt app run infsh/kokoro-tts --input '{
  "prompt": "<chunk-2>",
  "voice": "bf_emma"
}' > chunk2.json
 
# Merge chunks
belt app run infsh/media-merger --input '{
  "audio_files": ["<chunk1-url>", "<chunk2-url>"],
  "crossfade_ms": 100
}'

# 1. Generate voiceover
belt app run infsh/kokoro-tts --input '{
  "prompt": "This stunning footage shows the beauty of nature in its purest form.",
  "voice": "am_michael"
}' > voiceover.json
 
# 2. Merge with video
belt app run infsh/media-merger --input '{
  "video_url": "https://your-video.mp4",
  "audio_url": "<voiceover-url>"
}'

# 1. Generate speech
belt app run infsh/kokoro-tts --input '{
  "prompt": "Hi, Im excited to share some updates with you today.",
  "voice": "af_sarah"
}' > speech.json
 
# 2. Animate with avatar
belt app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "<speech-url>"
}'

# Slow narration
belt app run infsh/kokoro-tts --input '{
  "prompt": "Take a deep breath. Let yourself relax.",
  "voice": "bf_emma",
  "speed": 0.8
}'

belt app run infsh/kokoro-tts --input '{
  "prompt": "Wait... Did you hear that? Something is coming. Something big!",
  "voice": "am_adam"
}'

# ElevenLabs TTS (premium, 22+ voices)
npx skills add inference-sh/skills@elevenlabs-tts
 
# ElevenLabs voice changer (transform recordings)
npx skills add inference-sh/skills@elevenlabs-voice-changer
 
# All TTS models
npx skills add inference-sh/skills@text-to-speech
 
# Podcast creation
npx skills add inference-sh/skills@ai-podcast-creation
 
# AI avatars
npx skills add inference-sh/skills@ai-avatar-video
 
# Video generation
npx skills add inference-sh/skills@ai-video-generation
 
# Full platform skill
npx skills add inference-sh/skills@infsh-cli