{"skill":{"slug":"ai-podcast-creation","displayName":"Ai Podcast Creation","summary":"Create AI-powered podcasts with text-to-speech, music, and audio editing. Tools: Kokoro TTS, DIA TTS, Chatterbox, AI music generation, media merger. Capabili...","description":"---\nname: ai-podcast-creation\ndescription: \"Create AI-powered podcasts with text-to-speech, music, and audio editing. Tools: Kokoro TTS, DIA TTS, Chatterbox, AI music generation, media merger. Capabilities: multi-voice conversations, background music, intro/outro, full episodes. Use for: podcast production, audiobooks, voice content, audio newsletters. Triggers: podcast, ai podcast, text to speech podcast, audio content, voice over, ai audiobook, multi voice, conversation ai, notebooklm alternative, audio generation, podcast automation, ai narrator, voice content, audio newsletter, podcast maker\"\nallowed-tools: Bash(infsh *)\n---\n\n# AI Podcast Creation\n\nCreate AI-powered podcasts and audio content via [inference.sh](https://inference.sh) CLI.\n\n![AI Podcast Creation](https://cloud.inference.sh/u/4mg21r6ta37mpaz6ktzwtt8krr/01jz00krptarq4bwm89g539aea.png)\n\n## Quick Start\n\n```bash\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Generate podcast segment\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Welcome to the AI Frontiers podcast. Today we explore the latest developments in generative AI.\",\n  \"voice\": \"am_michael\"\n}'\n```\n\n> **Install note:** The [install script](https://cli.inference.sh) 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](https://dist.inference.sh/cli/checksums.txt) available.\n\n## Available Voices\n\n### Kokoro TTS\n\n| Voice ID | Description | Best For |\n|----------|-------------|----------|\n| `af_sarah` | American female, warm | Host, narrator |\n| `af_nicole` | American female, professional | News, business |\n| `am_michael` | American male, authoritative | Documentary, tech |\n| `am_adam` | American male, conversational | Casual podcast |\n| `bf_emma` | British female, refined | Audiobooks |\n| `bm_george` | British male, classic | Formal content |\n\n### DIA TTS (Conversational)\n\n| Voice ID | Description | Best For |\n|----------|-------------|----------|\n| `dia-conversational` | Natural conversation | Dialogue, interviews |\n\n### Chatterbox\n\n| Voice ID | Description | Best For |\n|----------|-------------|----------|\n| `chatterbox-default` | Expressive | Casual, entertainment |\n\n## Podcast Workflows\n\n### Simple Narration\n\n```bash\n# Single voice podcast segment\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Your podcast script here. Make it conversational and engaging. Add natural pauses with punctuation.\",\n  \"voice\": \"am_michael\"\n}'\n```\n\n### Multi-Voice Conversation\n\n```bash\n# Host introduction\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Welcome back to Tech Talk. Today I have a special guest to discuss AI developments.\",\n  \"voice\": \"am_michael\"\n}' > host_intro.json\n\n# Guest response\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Thanks for having me. I am excited to share what we have been working on.\",\n  \"voice\": \"af_sarah\"\n}' > guest_response.json\n\n# Merge into conversation\ninfsh app run infsh/media-merger --input '{\n  \"audio_files\": [\"<host-url>\", \"<guest-url>\"],\n  \"crossfade_ms\": 500\n}'\n```\n\n### Full Episode Pipeline\n\n```bash\n# 1. Generate script with Claude\ninfsh app run openrouter/claude-sonnet-45 --input '{\n  \"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.\"\n}' > script.json\n\n# 2. Generate intro music\ninfsh app run infsh/ai-music --input '{\n  \"prompt\": \"Podcast intro music, upbeat, modern, tech feel, 15 seconds\"\n}' > intro_music.json\n\n# 3. Generate host segments\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"<host-lines>\",\n  \"voice\": \"am_michael\"\n}' > host.json\n\n# 4. Generate guest segments\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"<guest-lines>\",\n  \"voice\": \"af_sarah\"\n}' > guest.json\n\n# 5. Generate outro music\ninfsh app run infsh/ai-music --input '{\n  \"prompt\": \"Podcast outro music, matching intro style, fade out, 10 seconds\"\n}' > outro_music.json\n\n# 6. Merge everything\ninfsh app run infsh/media-merger --input '{\n  \"audio_files\": [\n    \"<intro-music>\",\n    \"<host>\",\n    \"<guest>\",\n    \"<outro-music>\"\n  ],\n  \"crossfade_ms\": 1000\n}'\n```\n\n### NotebookLM-Style Content\n\nGenerate podcast-style discussions from documents.\n\n```bash\n# 1. Extract key points\ninfsh app run openrouter/claude-sonnet-45 --input '{\n  \"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>\"\n}' > discussion_script.json\n\n# 2. Generate Host A\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"<host-a-lines>\",\n  \"voice\": \"am_michael\"\n}' > host_a.json\n\n# 3. Generate Host B\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"<host-b-lines>\",\n  \"voice\": \"af_sarah\"\n}' > host_b.json\n\n# 4. Interleave and merge\ninfsh app run infsh/media-merger --input '{\n  \"audio_files\": [\"<host-a-1>\", \"<host-b-1>\", \"<host-a-2>\", \"<host-b-2>\"],\n  \"crossfade_ms\": 300\n}'\n```\n\n### Audiobook Chapter\n\n```bash\n# Long-form narration\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"Chapter One. It was a dark and stormy night when the first AI achieved consciousness...\",\n  \"voice\": \"bf_emma\",\n  \"speed\": 0.9\n}'\n```\n\n## Audio Enhancement\n\n### Add Background Music\n\n```bash\n# 1. Generate podcast audio\ninfsh app run infsh/kokoro-tts --input '{\n  \"text\": \"<podcast-script>\",\n  \"voice\": \"am_michael\"\n}' > podcast.json\n\n# 2. Generate ambient music\ninfsh app run infsh/ai-music --input '{\n  \"prompt\": \"Soft ambient background music for podcast, subtle, non-distracting, loopable\"\n}' > background.json\n\n# 3. Mix with lower background volume\ninfsh app run infsh/media-merger --input '{\n  \"audio_files\": [\"<podcast-url>\"],\n  \"background_audio\": \"<background-url>\",\n  \"background_volume\": 0.15\n}'\n```\n\n### Add Sound Effects\n\n```bash\n# Transition sounds between segments\ninfsh app run infsh/ai-music --input '{\n  \"prompt\": \"Short podcast transition sound, whoosh, 2 seconds\"\n}' > transition.json\n```\n\n## Script Writing Tips\n\n### Prompt for Claude\n\n```bash\ninfsh app run openrouter/claude-sonnet-45 --input '{\n  \"prompt\": \"Write a podcast script with these requirements:\n  - Topic: [YOUR TOPIC]\n  - Duration: 5 minutes (about 750 words)\n  - Format: Two hosts (HOST_A and HOST_B)\n  - Tone: Conversational, informative, engaging\n  - Include: Hook intro, 3 main points, call to action\n  - Mark speaker changes clearly\n\n  Make it sound natural, not scripted. Add verbal fillers like \\\"you know\\\" and \\\"I mean\\\" occasionally.\"\n}'\n```\n\n## Podcast Templates\n\n### Interview Format\n\n```\nHOST: Introduction and welcome\nGUEST: Thank you, happy to be here\nHOST: First question about background\nGUEST: Response with story\nHOST: Follow-up question\nGUEST: Deeper insight\n... continue pattern ...\nHOST: Closing question\nGUEST: Final thoughts\nHOST: Thank you and outro\n```\n\n### Solo Episode\n\n```\nIntroduction with hook\nTopic overview\nPoint 1 with examples\nPoint 2 with examples\nPoint 3 with examples\nSummary and takeaways\nCall to action\nOutro\n```\n\n### News Roundup\n\n```\nIntro music\nWelcome and date\nStory 1: headline + details\nStory 2: headline + details\nStory 3: headline + details\nAnalysis/opinion segment\nOutro\n```\n\n## Best Practices\n\n1. **Natural punctuation** - Use commas and periods for pacing\n2. **Short sentences** - Easier to speak and listen\n3. **Varied voices** - Different speakers prevent monotony\n4. **Background music** - Subtle, at 10-15% volume\n5. **Crossfades** - Smooth transitions between segments\n6. **Edit scripts** - Remove filler before generating\n\n## Related Skills\n\n```bash\n# Text-to-speech models\nnpx skills add inference-sh/skills@text-to-speech\n\n# AI music generation\nnpx skills add inference-sh/skills@ai-music-generation\n\n# LLM for scripts\nnpx skills add inference-sh/skills@llm-models\n\n# Content pipelines\nnpx skills add inference-sh/skills@ai-content-pipeline\n\n# Full platform skill\nnpx skills add inference-sh/skills@inference-sh\n```\n\nBrowse all apps: `infsh app list --category audio`\n","tags":{"latest":"0.1.5"},"stats":{"comments":0,"downloads":2142,"installsAllTime":8,"installsCurrent":8,"stars":2,"versions":2},"createdAt":1770363061080,"updatedAt":1778988655645},"latestVersion":{"version":"0.1.5","createdAt":1771403016728,"changelog":"- Added a comprehensive SKILL.md with detailed usage examples, available voices, and workflow templates for AI-powered podcast creation.\n- Documented all supported tools: Kokoro TTS, DIA TTS, Chatterbox, AI music generation, and audio merging.\n- Included step-by-step guides for single-voice, multi-voice conversations, full episode pipelines, and audiobooks.\n- Provided best practices, script writing prompts, and podcast episode templates.\n- Outlined enrichment features like background music, sound effects, and audio post-processing.","license":null},"metadata":null,"owner":{"handle":"okaris","userId":"s1737xapsjy8k5qnagtfyf5nrx85t72x","displayName":"Ömer Karışman","image":"https://avatars.githubusercontent.com/u/1448702?v=4"},"moderation":null}