Ai Voice Cloning

AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: Kokoro TTS, DIA, Chatterbox, Higgs, VibeVoice for natural speech. Capa...

Security Scan

The skill's stated purpose (TTS / voice cloning) matches its instructions, but it tells the agent to download and run a remote install script and to log in to a third‑party service (inference.sh) without declaring credentials or describing privacy/verification details — this creates disproportionate risk and missing information.

Purpose & Capability

Name/description align with the instructions: the SKILL.md consistently describes using the inference.sh CLI and specific TTS models for voice generation and related workflows.

Instruction Scope

Runtime instructions tell the agent to run a remote installer (curl | sh), run 'infsh login', and call infsh apps which will send text/audio to inference.sh and other named apps (e.g., bytedance/omnihuman-1-5). The document does not discuss what data is transmitted, where it is stored, or what credentials are required — broad network I/O and credential usage are implicit but undocumented.

Install Mechanism

No local code is bundled; the Quick Start pipes a remote script from https://cli.inference.sh to sh and downloads binaries from dist.inference.sh. Piping remote scripts to a shell is high-risk unless the script and checksums are audited; the installer domain is not a well-known package host and the skill provides no embedded verification steps aside from pointing to a checksums.txt.

Credentials

Registry metadata declares no required env vars or credentials, yet instructions call 'infsh login' (implying user credentials or tokens will be created/stored). This mismatch hides required credentials and the agent's runtime will interact with external services that may receive potentially sensitive text/audio input.

Persistence & Privilege

always is false and there are no install scripts embedded in the skill itself. The skill does not request persistent or elevated platform privileges in the metadata.

What to consider before installing

This skill appears to do what it says (voice synthesis) but requires installing and using a remote CLI (curl | sh https://cli.inference.sh) and logging into inference.sh — actions that will transmit your text/audio to an external service and will store credentials locally. Before installing, review the installer script and checksums at the referenced URLs, prefer manual download + checksum verification over piping to sh, and confirm the service's privacy/retention policy and terms of use. Avoid sending any sensitive or proprietary text/audio to the service until you trust it. If you need a lower-risk option, consider a local/offline TTS solution or a CLI from a known package registry; if you still want this skill, ask the maintainer for source code or a signed release and verify the install artifacts in a sandbox first.

AI Voice Generation

Generate natural AI voices via inference.sh CLI.

Quick Start

curl -fsSL https://cli.inference.sh | sh && infsh login

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

Install note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.

Available Models

Model	App ID	Best For
Kokoro TTS	infsh/kokoro-tts	Natural, multiple voices
DIA	infsh/dia-tts	Conversational, expressive
Chatterbox	infsh/chatterbox	Casual, entertainment
Higgs	infsh/higgs-tts	Professional narration
VibeVoice	infsh/vibevoice	Emotional range

Kokoro Voice Library

American English

Voice ID	Gender	Style
af_sarah	Female	Warm, friendly
af_nicole	Female	Professional
af_sky	Female	Youthful
am_michael	Male	Authoritative
am_adam	Male	Conversational
am_echo	Male	Clear, neutral

British English

Voice ID	Gender	Style
bf_emma	Female	Refined
bf_isabella	Female	Warm
bm_george	Male	Classic
bm_lewis	Male	Modern

Voice Generation Examples

Professional Narration

infsh app run infsh/kokoro-tts --input '{
  "text": "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

infsh 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

infsh app run infsh/kokoro-tts --input '{
  "text": "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
}'

Video Voiceover

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

Podcast Host

infsh app run infsh/kokoro-tts --input '{
  "text": "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

# Generate dialogue between two speakers
# Speaker 1
infsh app run infsh/kokoro-tts --input '{
  "text": "Have you seen the latest AI developments? Its incredible how fast things are moving.",
  "voice": "am_michael"
}' > speaker1.json

# Speaker 2
infsh app run infsh/kokoro-tts --input '{
  "text": "I know, right? Just last week I tried that new image generator and was blown away.",
  "voice": "af_sarah"
}' > speaker2.json

# Merge conversation
infsh app run infsh/media-merger --input '{
  "audio_files": ["<speaker1-url>", "<speaker2-url>"],
  "crossfade_ms": 300
}'

Long-Form Content

Chunked Processing

For content over 5000 characters, split into chunks:

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

# Split and generate
# Chunk 1
infsh app run infsh/kokoro-tts --input '{
  "text": "<chunk-1>",
  "voice": "bf_emma"
}' > chunk1.json

# Chunk 2
infsh app run infsh/kokoro-tts --input '{
  "text": "<chunk-2>",
  "voice": "bf_emma"
}' > chunk2.json

# Merge chunks
infsh app run infsh/media-merger --input '{
  "audio_files": ["<chunk1-url>", "<chunk2-url>"],
  "crossfade_ms": 100
}'

Voice + Video Workflow

Add Voiceover to Video

# 1. Generate voiceover
infsh app run infsh/kokoro-tts --input '{
  "text": "This stunning footage shows the beauty of nature in its purest form.",
  "voice": "am_michael"
}' > voiceover.json

# 2. Merge with video
infsh app run infsh/media-merger --input '{
  "video_url": "https://your-video.mp4",
  "audio_url": "<voiceover-url>"
}'

Create Talking Head

# 1. Generate speech
infsh app run infsh/kokoro-tts --input '{
  "text": "Hi, Im excited to share some updates with you today.",
  "voice": "af_sarah"
}' > speech.json

# 2. Animate with avatar
infsh app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "<speech-url>"
}'

Speed and Pacing

Speed	Effect	Use For
0.8	Slow, deliberate	Audiobooks, meditation
0.9	Slightly slow	Education, tutorials
1.0	Normal	General purpose
1.1	Slightly fast	Commercials, energy
1.2	Fast	Quick announcements

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

Punctuation for Pacing

Use punctuation to control speech rhythm:

Punctuation	Effect
Period .	Full pause
Comma ,	Brief pause
...	Extended pause
!	Emphasis
?	Question intonation
-	Quick break

infsh app run infsh/kokoro-tts --input '{
  "text": "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

# 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@inference-sh

Browse audio apps: infsh app list --category audio