Ai Voice Cloning

Install the belt CLI skill: npx skills add belt-sh/cli

AI Voice Generation

Generate natural AI voices via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions

bashCopy code
belt login

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

Available Models

Kokoro Voice Library

American English

British English

Inworld TTS — Character & Emotion Voices

Inworld TTS-2 is purpose-built for character voices, gaming, and expressive speech. Use [brackets] inline for emotion, non-verbals, and delivery control:

bashCopy code
# 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"
}'

Delivery modes: STABLE (consistent, narration), BALANCED (natural, default), CREATIVE (expressive, characters)

Steering examples: [laugh], [sigh], [whisper], [excited], [sad], [angry], [pause], [gasp]

Built-in voices (271+ across 15 languages): Sarah, Alex, Ashley, Dennis, Hana, Blake, Luna, Clive, and many more. Browse all at the Inworld TTS Playground.

Low-Latency for Real-Time / Conversational AI

bashCopy code
# 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
}'

Voice Generation Examples

Professional Narration

bashCopy code
belt app run falai/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
}'

Conversational Style

bashCopy code
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"
}'

Audiobook Narration

bashCopy code
belt app run falai/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",
  "language": "british-english",
  "speed": 0.9
}'

Video Voiceover

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

Podcast Host

bashCopy code
belt app run falai/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"
}'

Multi-Voice Conversation

bashCopy code
# Generate dialogue between two speakers
# Speaker 1
belt app run falai/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 falai/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 (no inference.sh app concatenates audio; use ffmpeg locally)
curl -L -o speaker1.mp3 "<speaker1-url>"
curl -L -o speaker2.mp3 "<speaker2-url>"
ffmpeg -i speaker1.mp3 -i speaker2.mp3 -filter_complex "acrossfade=d=0.3" conversation.mp3

Long-Form Content

Chunked Processing

For content over 5000 characters, split into chunks:

bashCopy code
# Process long text in chunks
TEXT="Your very long text here..."

# Split and generate
# Chunk 1
belt app run falai/kokoro-tts --input '{
  "prompt": "<chunk-1>",
  "voice": "bf_emma",
  "language": "british-english"
}' > chunk1.json

# Chunk 2
belt app run falai/kokoro-tts --input '{
  "prompt": "<chunk-2>",
  "voice": "bf_emma",
  "language": "british-english"
}' > chunk2.json

# Merge chunks (no inference.sh app concatenates audio; use ffmpeg locally)
curl -L -o chunk1.mp3 "<chunk1-url>"
curl -L -o chunk2.mp3 "<chunk2-url>"
ffmpeg -i chunk1.mp3 -i chunk2.mp3 -filter_complex "acrossfade=d=0.1" narration.mp3

Voice + Video Workflow

Add Voiceover to Video

bashCopy code
# 1. Generate voiceover
belt app run falai/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/video-audio-merger --input '{
  "video_file": "https://your-video.mp4",
  "audio_file": "<voiceover-url>"
}'

Create Talking Head

bashCopy code
# 1. Generate speech
belt app run falai/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": "https://portrait.jpg",
  "audio": "<speech-url>"
}'

Speed and Pacing

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

Punctuation for Pacing

Use punctuation to control speech rhythm:

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

Best Practices

1. Match voice to content - Professional voice for business, casual for social
2. Use punctuation - Control pacing with periods and commas
3. Keep sentences short - Easier to generate and sounds more natural
4. Test different voices - Same text sounds different across voices
5. Adjust speed - Slightly slower often sounds more natural
6. Break long content - Process in chunks for consistency

Use Cases

• Voiceovers - Video narration, commercials
• Audiobooks - Full book narration
• Podcasts - AI hosts and guests
• E-learning - Course narration
• Accessibility - Screen reader content
• IVR - Phone system messages
• Content localization - Translate and voice

Related Skills

bashCopy code
# 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

Browse audio apps: belt app list --category audio