Back to Details

ai-podcast-creation

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

AI Podcast Creation

AI播客创建

Create AI-powered podcasts and audio content via inference.sh CLI.
AI Podcast Creation
通过inference.sh CLI创建AI驱动的播客及音频内容。
AI Podcast Creation

Quick Start

快速开始

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

Generate podcast segment

生成播客片段

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" }'
undefined
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" }'
undefined

Available Voices

可用语音

Kokoro TTS

Kokoro TTS

Voice IDDescriptionBest For
af_sarah
American female, warmHost, narrator
af_nicole
American female, professionalNews, business
am_michael
American male, authoritativeDocumentary, tech
am_adam
American male, conversationalCasual podcast
bf_emma
British female, refinedAudiobooks
bm_george
British male, classicFormal content
语音ID描述适用场景
af_sarah
美国女性，温暖风格主播、旁白
af_nicole
美国女性，专业风格新闻、商务内容
am_michael
美国男性，权威风格纪录片、科技内容
am_adam
美国男性，口语化风格休闲播客
bf_emma
英国女性，优雅风格有声书
bm_george
英国男性，经典风格正式内容

DIA TTS (Conversational)

DIA TTS（对话风格）

Voice IDDescriptionBest For
dia-conversational
Natural conversationDialogue, interviews
语音ID描述适用场景
dia-conversational
自然对话风格对话、访谈内容

Chatterbox

Chatterbox

Voice IDDescriptionBest For
chatterbox-default
ExpressiveCasual, entertainment
语音ID描述适用场景
chatterbox-default
富有表现力休闲、娱乐内容

Podcast Workflows

播客工作流

Simple Narration

单语音旁白

bash
undefined
bash
undefined

Single voice podcast segment

单语音播客片段

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" }'
undefined
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" }'
undefined

Multi-Voice Conversation

多角色语音对话

bash
undefined
bash
undefined

Host introduction

主播开场白

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
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

嘉宾回应

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
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

合并为对话内容

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

Full Episode Pipeline

完整剧集制作流程

bash
undefined
bash
undefined

1. Generate script with Claude

1. 用Claude生成脚本

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
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

2. 生成片头音乐

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

3. Generate host segments

3. 生成主播片段

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

4. Generate guest segments

4. 生成嘉宾片段

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

5. Generate outro music

5. 生成片尾音乐

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

6. Merge everything

6. 合并所有内容

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

NotebookLM-Style Content

NotebookLM风格内容

Generate podcast-style discussions from documents.
bash
undefined
基于文档生成播客风格的讨论内容。
bash
undefined

1. Extract key points

1. 提取关键要点

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
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

2. 生成主播A内容

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

3. Generate Host B

3. 生成主播B内容

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

4. Interleave and merge

4. 交错合并内容

infsh app run infsh/media-merger --input '{ "audio_files": ["<host-a-1>", "<host-b-1>", "<host-a-2>", "<host-b-2>"], "crossfade_ms": 300 }'
undefined
infsh app run infsh/media-merger --input '{ "audio_files": ["<host-a-1>", "<host-b-1>", "<host-a-2>", "<host-b-2>"], "crossfade_ms": 300 }'
undefined

Audiobook Chapter

有声书章节

bash
undefined
bash
undefined

Long-form narration

长篇旁白内容

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 }'
undefined
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 }'
undefined

Audio Enhancement

音频优化

Add Background Music

添加背景音乐

bash
undefined
bash
undefined

1. Generate podcast audio

1. 生成播客音频

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

2. Generate ambient music

2. 生成环境音乐

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

3. 混合音频并降低背景音乐音量

infsh app run infsh/media-merger --input '{ "audio_files": ["<podcast-url>"], "background_audio": "<background-url>", "background_volume": 0.15 }'
undefined
infsh app run infsh/media-merger --input '{ "audio_files": ["<podcast-url>"], "background_audio": "<background-url>", "background_volume": 0.15 }'
undefined

Add Sound Effects

添加音效

bash
undefined
bash
undefined

Transition sounds between segments

片段间过渡音效

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

Script Writing Tips

脚本编写技巧

Prompt for Claude

用于Claude的提示词

bash
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."
}'
bash
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

播客模板

Interview Format

访谈格式

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
主播：开场介绍与欢迎
嘉宾：致谢，表达参与喜悦
主播：第一个关于背景的问题
嘉宾：结合故事回应
主播：跟进问题
嘉宾：分享深度见解
... 重复上述模式 ...
主播：收尾问题
嘉宾：最终观点
主播：致谢与片尾

Solo Episode

单人剧集

Introduction with hook
Topic overview
Point 1 with examples
Point 2 with examples
Point 3 with examples
Summary and takeaways
Call to action
Outro
带吸引力的开场
主题概述
要点1及示例
要点2及示例
要点3及示例
总结与收获
行动号召
片尾

News Roundup

新闻汇总

Intro music
Welcome and date
Story 1: headline + details
Story 2: headline + details
Story 3: headline + details
Analysis/opinion segment
Outro
片头音乐
欢迎语与日期
新闻1：标题+详情
新闻2：标题+详情
新闻3：标题+详情
分析/观点环节
片尾

Best Practices

最佳实践

  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
  1. 自然标点 - 使用逗号和句号控制语速
  2. 短句表达 - 更易于朗读和收听
  3. 语音多样化 - 不同主播避免单调
  4. 背景音乐 - 音量保持在10-15%，避免干扰
  5. 交叉淡入淡出 - 实现片段间的平滑过渡
  6. 脚本编辑 - 生成前删除冗余内容

Related Skills

相关技能

bash
undefined
bash
undefined

Text-to-speech models

文本转语音模型

npx skills add inference-sh/skills@text-to-speech
npx skills add inference-sh/skills@text-to-speech

AI music generation

AI音乐生成

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

LLM for scripts

大语言模型脚本生成

npx skills add inference-sh/skills@llm-models
npx skills add inference-sh/skills@llm-models

Content pipelines

内容流水线

npx skills add inference-sh/skills@ai-content-pipeline
npx skills add inference-sh/skills@ai-content-pipeline

Full platform skill

完整平台技能

npx skills add inference-sh/skills@inference-sh

Browse all apps: `infsh app list --category audio`
npx skills add inference-sh/skills@inference-sh

浏览所有音频类应用：`infsh app list --category audio`