Ai Podcast Creation

Create AI-powered podcasts with text-to-speech, music, and audio editing. Tools: Kokoro TTS, DIA TTS, Chatterbox, AI music generation, media merger. Capabili...

Security Scan

The skill’s instructions line up with podcast creation, but they ask the agent to download and run a third‑party CLI (via curl | sh) from non-obvious domains and reference external LLM/TTS services without declaring required credentials — this combination is disproportionate and worth caution.

Purpose & Capability

The name/description (AI podcast creation with TTS, music, merging) matches the runtime instructions: invoking an inference.sh CLI to run TTS, music-generation, and media-merger apps. Requiring a CLI to orchestrate these services is coherent with the stated purpose.

Instruction Scope

The SKILL.md instructs the agent to install and run the inference.sh CLI, call multiple remote apps (e.g., infsh/kokoro-tts, infsh/ai-music, openrouter/claude-*), and suggests feeding document contents into a model. It does not instruct reading arbitrary local system files, but it does encourage piping and executing a remote installer (curl | sh) and sending content to external endpoints (inference.sh/openrouter). That means user data and scripts may be uploaded to third parties — the doc does not state where data is stored or how auth is done.

Install Mechanism

There is no packaged install spec in the registry; instead the SKILL.md tells users/agents to run `curl -fsSL https://cli.inference.sh | sh` and claims the installer downloads a binary from dist.inference.sh and verifies checksums. Both cli.inference.sh and dist.inference.sh are external domains (not standard package hosts like GitHub releases). 'curl | sh' and remote binary installation is a higher-risk install pattern because it executes network-fetched code. The SKILL.md's assurance about checksums is helpful but unverifiable from this manifest; no cryptographic signature or well-known distribution channel is documented.

Credentials

The skill declares no required environment variables or credentials, yet its examples invoke services that commonly require API keys (e.g., openrouter/claude-*, inference.sh apps). The manifest does not declare which credentials the infsh CLI or the referenced apps will need or where they are stored. This omission is disproportionate: an orchestration CLI that calls third-party models typically needs credentials and permission scopes, and the skill should state what it requires.

Persistence & Privilege

always:false and no install spec in the registry means the skill does not request forced permanent inclusion or elevated platform privileges. Autonomous model invocation is enabled by default (normal) but is not, on its own, a concern here. If combined with the remote installer and undeclared credentials, autonomy increases risk — note this when deciding whether to allow autonomous invocation.

What to consider before installing

This SKILL.md appears to implement its stated purpose, but exercise caution before running anything it suggests. Specific recommendations: - Do not run `curl | sh` on a host you care about; prefer to inspect the installer first or run in an isolated VM/container. - Independently verify the CLI binary and checksums via a trusted channel (project homepage, signed releases). The manifest provides dist.inference.sh and cli.inference.sh but those are not standard trusted hosts by default. - Ask the skill author (or maintainer) to declare required credentials and explain where credentials are stored and what endpoints will receive your audio/text data (privacy/data retention). - Expect that content you feed (scripts, documents, audio) will be transmitted to inference.sh/openrouter services; review their TOS/privacy before uploading sensitive material. - If you must test, do so with non-sensitive content and in a sandboxed environment. If you need higher assurance, request a version that uses an audit-able distribution (e.g., signed GitHub release) and that documents exact auth requirements.

Create AI-powered podcasts and audio content via inference.sh CLI.

Quick Start

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

# Generate podcast segment
infsh app run infsh/kokoro-tts --input '{
  "text": "Welcome to the AI Frontiers podcast. Today we explore the latest developments in generative AI.",
  "voice": "am_michael"
}'

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 Voices

Kokoro TTS

Voice ID	Description	Best For
af_sarah	American female, warm	Host, narrator
af_nicole	American female, professional	News, business
am_michael	American male, authoritative	Documentary, tech
am_adam	American male, conversational	Casual podcast
bf_emma	British female, refined	Audiobooks
bm_george	British male, classic	Formal content

DIA TTS (Conversational)

Voice ID	Description	Best For
dia-conversational	Natural conversation	Dialogue, interviews

Chatterbox

Voice ID	Description	Best For
chatterbox-default	Expressive	Casual, entertainment

Podcast Workflows

Simple Narration

# Single voice podcast segment
infsh app run infsh/kokoro-tts --input '{
  "text": "Your podcast script here. Make it conversational and engaging. Add natural pauses with punctuation.",
  "voice": "am_michael"
}'

Multi-Voice Conversation

# Host introduction
infsh app run infsh/kokoro-tts --input '{
  "text": "Welcome back to Tech Talk. Today I have a special guest to discuss AI developments.",
  "voice": "am_michael"
}' > host_intro.json

# Guest response
infsh app run infsh/kokoro-tts --input '{
  "text": "Thanks for having me. I am excited to share what we have been working on.",
  "voice": "af_sarah"
}' > guest_response.json

# Merge into conversation
infsh app run infsh/media-merger --input '{
  "audio_files": ["<host-url>", "<guest-url>"],
  "crossfade_ms": 500
}'

Full Episode Pipeline

# 1. Generate script with Claude
infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Write a 5-minute podcast script about the impact of AI on creative work. Format as a two-person dialogue between HOST and GUEST. Include natural conversation, questions, and insights."
}' > script.json

# 2. Generate intro music
infsh app run infsh/ai-music --input '{
  "prompt": "Podcast intro music, upbeat, modern, tech feel, 15 seconds"
}' > intro_music.json

# 3. Generate host segments
infsh app run infsh/kokoro-tts --input '{
  "text": "<host-lines>",
  "voice": "am_michael"
}' > host.json

# 4. Generate guest segments
infsh app run infsh/kokoro-tts --input '{
  "text": "<guest-lines>",
  "voice": "af_sarah"
}' > guest.json

# 5. Generate outro music
infsh app run infsh/ai-music --input '{
  "prompt": "Podcast outro music, matching intro style, fade out, 10 seconds"
}' > outro_music.json

# 6. Merge everything
infsh app run infsh/media-merger --input '{
  "audio_files": [
    "<intro-music>",
    "<host>",
    "<guest>",
    "<outro-music>"
  ],
  "crossfade_ms": 1000
}'

NotebookLM-Style Content

Generate podcast-style discussions from documents.

# 1. Extract key points
infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Read this document and create a podcast script where two hosts discuss the key points in an engaging, conversational way. Include questions, insights, and natural dialogue.\n\nDocument:\n<your-document-content>"
}' > discussion_script.json

# 2. Generate Host A
infsh app run infsh/kokoro-tts --input '{
  "text": "<host-a-lines>",
  "voice": "am_michael"
}' > host_a.json

# 3. Generate Host B
infsh app run infsh/kokoro-tts --input '{
  "text": "<host-b-lines>",
  "voice": "af_sarah"
}' > host_b.json

# 4. Interleave and merge
infsh app run infsh/media-merger --input '{
  "audio_files": ["<host-a-1>", "<host-b-1>", "<host-a-2>", "<host-b-2>"],
  "crossfade_ms": 300
}'

Audiobook Chapter

# Long-form narration
infsh app run infsh/kokoro-tts --input '{
  "text": "Chapter One. It was a dark and stormy night when the first AI achieved consciousness...",
  "voice": "bf_emma",
  "speed": 0.9
}'

Audio Enhancement

Add Background Music

# 1. Generate podcast audio
infsh app run infsh/kokoro-tts --input '{
  "text": "<podcast-script>",
  "voice": "am_michael"
}' > podcast.json

# 2. Generate ambient music
infsh app run infsh/ai-music --input '{
  "prompt": "Soft ambient background music for podcast, subtle, non-distracting, loopable"
}' > background.json

# 3. Mix with lower background volume
infsh app run infsh/media-merger --input '{
  "audio_files": ["<podcast-url>"],
  "background_audio": "<background-url>",
  "background_volume": 0.15
}'

Add Sound Effects

# Transition sounds between segments
infsh app run infsh/ai-music --input '{
  "prompt": "Short podcast transition sound, whoosh, 2 seconds"
}' > transition.json

Script Writing Tips

Prompt for Claude

infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Write a podcast script with these requirements:
  - Topic: [YOUR TOPIC]
  - Duration: 5 minutes (about 750 words)
  - Format: Two hosts (HOST_A and HOST_B)
  - Tone: Conversational, informative, engaging
  - Include: Hook intro, 3 main points, call to action
  - Mark speaker changes clearly

  Make it sound natural, not scripted. Add verbal fillers like \"you know\" and \"I mean\" occasionally."
}'

Podcast Templates

Interview Format

HOST: Introduction and welcome
GUEST: Thank you, happy to be here
HOST: First question about background
GUEST: Response with story
HOST: Follow-up question
GUEST: Deeper insight
... continue pattern ...
HOST: Closing question
GUEST: Final thoughts
HOST: Thank you and outro

Solo Episode

Introduction with hook
Topic overview
Point 1 with examples
Point 2 with examples
Point 3 with examples
Summary and takeaways
Call to action
Outro

News Roundup

Intro music
Welcome and date
Story 1: headline + details
Story 2: headline + details
Story 3: headline + details
Analysis/opinion segment
Outro

Best Practices

1. Natural punctuation - Use commas and periods for pacing
2. Short sentences - Easier to speak and listen
3. Varied voices - Different speakers prevent monotony
4. Background music - Subtle, at 10-15% volume
5. Crossfades - Smooth transitions between segments
6. Edit scripts - Remove filler before generating

Related Skills

# Text-to-speech models
npx skills add inference-sh/skills@text-to-speech

# AI music generation
npx skills add inference-sh/skills@ai-music-generation

# LLM for scripts
npx skills add inference-sh/skills@llm-models

# Content pipelines
npx skills add inference-sh/skills@ai-content-pipeline

# Full platform skill
npx skills add inference-sh/skills@inference-sh

Browse all apps: infsh app list --category audio