ai-podcast-creation

belt CLI スキルをインストール： npx skills add belt-sh/cli

AI ポッドキャストの作成

inference.sh CLI を使って、AI を活用したポッドキャストや音声コンテンツを作成します。

クイックスタート

inference.sh CLI（belt）が必要です。インストール手順

belt login

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

利用可能な音声

Kokoro TTS

音声 ID	説明	最適な用途
af_sarah	アメリカ英語の女性、温かみのある声	ホスト、ナレーター
af_nicole	アメリカ英語の女性、プロフェッショナルな声	ニュース、ビジネス
am_michael	アメリカ英語の男性、威厳のある声	ドキュメンタリー、テクノロジー
am_adam	アメリカ英語の男性、会話調の声	カジュアルなポッドキャスト
bf_emma	イギリス英語の女性、上品な声	オーディオブック
bm_george	イギリス英語の男性、古典的な声	フォーマルなコンテンツ

DIA TTS（会話向け）

音声 ID	説明	最適な用途
dia-conversational	自然な会話	対話、インタビュー

Chatterbox

音声 ID	説明	最適な用途
chatterbox-default	表現豊かな声	カジュアル、エンターテインメント

ポッドキャストのワークフロー

シンプルなナレーション

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

複数の音声による会話

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

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

# Merge into conversation (no inference.sh app concatenates audio; use ffmpeg locally)
curl -L -o host.mp3 "<host-url>"
curl -L -o guest.mp3 "<guest-url>"
ffmpeg -i host.mp3 -i guest.mp3 -filter_complex "acrossfade=d=0.5" conversation.mp3

エピソード全体の制作パイプライン

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

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

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

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

# 6. Merge everything (no inference.sh app concatenates audio; use ffmpeg locally)
curl -L -o intro.mp3 "<intro-music>"
curl -L -o host.mp3 "<host>"
curl -L -o guest.mp3 "<guest>"
curl -L -o outro.mp3 "<outro-music>"
ffmpeg -i intro.mp3 -i host.mp3 -i guest.mp3 -i outro.mp3 -filter_complex \
  "[0][1]acrossfade=d=1[a];[a][2]acrossfade=d=1[b];[b][3]acrossfade=d=1" episode.mp3

NotebookLM 風のコンテンツ

ドキュメントからポッドキャスト形式のディスカッションを生成します。

# 1. Extract key points
belt 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
belt app run falai/kokoro-tts --input '{
  "prompt": "<host-a-lines>",
  "voice": "am_michael"
}' > host_a.json

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

# 4. Interleave and merge (no inference.sh app concatenates audio; use ffmpeg locally)
curl -L -o a1.mp3 "<host-a-1>"; curl -L -o b1.mp3 "<host-b-1>"
curl -L -o a2.mp3 "<host-a-2>"; curl -L -o b2.mp3 "<host-b-2>"
ffmpeg -i a1.mp3 -i b1.mp3 -i a2.mp3 -i b2.mp3 -filter_complex \
  "[0][1]acrossfade=d=0.3[a];[a][2]acrossfade=d=0.3[b];[b][3]acrossfade=d=0.3" conversation.mp3

オーディオブックの章

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

音声の加工

BGM を追加

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

# 2. Generate ambient music
belt 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 (no inference.sh app mixes audio; use ffmpeg locally)
curl -L -o podcast.mp3 "<podcast-url>"
curl -L -o background.mp3 "<background-url>"
ffmpeg -i podcast.mp3 -stream_loop -1 -i background.mp3 -filter_complex \
  "[1]volume=0.15[bg];[0][bg]amix=inputs=2:duration=first" mixed.mp3

効果音を追加

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

スクリプト作成のヒント

Claude 向けプロンプト

belt 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."
}'

ポッドキャストのテンプレート

インタビュー形式

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

ソロエピソード

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

ニュースまとめ

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

ベストプラクティス

1. 自然な句読点 - 間を取るために読点や句点を使います
2. 短い文 - 話しやすく、聞き取りやすくなります
3. 音声に変化をつける - 話者を変えることで単調さを防げます
4. BGM - 控えめに、音量は 10～15％にします
5. クロスフェード - セグメント間を滑らかにつなぎます
6. スクリプトを編集する - 生成前に不要なつなぎ言葉を削除します

関連スキル

# 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@infsh-cli

すべてのアプリを表示：belt app list --category audio