ai-voice-cloning

安装 belt CLI 技能： npx skills add belt-sh/cli

AI 语音生成

通过 inference.sh CLI 生成自然的 AI 语音。

快速开始

需要 inference.sh CLI（belt）。安装说明

belt login

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

可用模型

模型	应用 ID	最适合
Inworld TTS-2	inworld/text-to-speech-2	100 多种语言、情绪／非语言引导、表达模式
Inworld TTS 1.5 Max	inworld/text-to-speech-1-5-max	低延迟（<200ms）、15 种语言
Inworld TTS 1.5 Mini	inworld/text-to-speech-1-5-mini	超低延迟（约 120ms）、15 种语言、实时处理
ElevenLabs TTS	elevenlabs/tts	优质音质、22 种以上声音、32 种语言
ElevenLabs Voice Changer	elevenlabs/voice-changer	转换现有语音录音
Kokoro TTS	infsh/kokoro-tts	自然、多种声音
DIA	infsh/dia-tts	对话式、富有表现力
Chatterbox	infsh/chatterbox	轻松随意、娱乐用途
Higgs	infsh/higgs-tts	专业旁白
VibeVoice	infsh/vibevoice	丰富的情感表达

Kokoro 声音库

美式英语

声音 ID	性别	风格
af_sarah	女	温暖、友好
af_nicole	女	专业
af_sky	女	青春
am_michael	男	权威
am_adam	男	对话式
am_echo	男	清晰、中性

英式英语

声音 ID	性别	风格
bf_emma	女	优雅
bf_isabella	女	温暖
bm_george	男	经典
bm_lewis	男	现代

Inworld TTS — 角色与情绪声音

Inworld TTS-2 专为角色配音、游戏和富有表现力的语音而打造。可在文本中使用 [brackets] 控制情绪、非语言表达和语音风格：

# Expressive character voice with emotion steering
belt app run inworld/text-to-speech-2 --input '{
  "text": "[excited] Oh wow, you actually found the ancient artifact! [gasp] I cannot believe it... [whisper] We need to keep this between us.",
  "voice_id": "Sarah",
  "delivery_mode": "CREATIVE"
}'

# Calm narrator with stable delivery
belt app run inworld/text-to-speech-2 --input '{
  "text": "The sun set behind the mountains, casting long shadows across the valley. A new chapter was about to begin.",
  "voice_id": "Sarah",
  "delivery_mode": "STABLE"
}'

表达模式： STABLE（稳定一致，适合旁白）、BALANCED（自然，默认）、CREATIVE（富有表现力，适合角色）

引导示例： [laugh]、[sigh]、[whisper]、[excited]、[sad]、[angry]、[pause]、[gasp]

内置声音（涵盖 15 种语言，271 种以上）：Sarah、Alex、Ashley、Dennis、Hana、Blake、Luna、Clive 等。前往 Inworld TTS Playground 查看全部声音。

面向实时／对话式 AI 的低延迟方案

# Ultra-fast response for chatbots & game NPCs (~120ms)
belt app run inworld/text-to-speech-1-5-mini --input '{
  "text": "Welcome, traveler. What brings you to our village?",
  "voice_id": "Clive",
  "speaking_rate": 0.9
}'

语音生成示例

专业旁白

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

对话风格

belt 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"
}'

有声书旁白

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

视频配音

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

播客主持人

belt app run infsh/kokoro-tts --input '{
  "prompt": "Welcome back to Tech Talk! Im your host, and today we are diving deep into the world of artificial intelligence.",
  "voice": "am_adam"
}'

多人语音对话

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

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

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

长篇内容

分块处理

对于超过 5000 个字符的内容，请拆分成多个块：

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

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

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

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

语音与视频工作流

为视频添加配音

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

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

创建口播视频

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

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

语速与节奏

语速	效果	用途
0.8	缓慢、从容	有声书、冥想
0.9	稍慢	教育、教程
1.0	正常	通用
1.1	稍快	广告、营造活力
1.2	快	快速通知

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

使用标点控制节奏

使用标点来控制语音节奏：

标点	效果
句号 .	完整停顿
逗号 ,	短暂停顿
...	延长停顿
!	强调
?	疑问语调
-	快速停顿

belt app run infsh/kokoro-tts --input '{
  "prompt": "Wait... Did you hear that? Something is coming. Something big!",
  "voice": "am_adam"
}'

最佳实践

1. 让语气与内容相符 - 商务内容使用专业语气，社交内容使用轻松语气
2. 使用标点符号 - 用句号和逗号控制语速
3. 保持句子简短 - 更容易生成，听起来也更自然
4. 测试不同的声音 - 同一段文本在不同声音下听起来会不一样
5. 调整语速 - 稍微放慢通常听起来更自然
6. 拆分较长内容 - 分段处理以保持一致性

使用场景

• 配音 - 视频旁白、商业广告
• 有声书 - 全书朗读
• 播客 - AI 主持人和嘉宾
• 在线学习 - 课程旁白
• 无障碍访问 - 屏幕阅读器内容
• IVR - 电话系统消息
• 内容本地化 - 翻译并配音

相关技能

# ElevenLabs TTS (premium, 22+ voices)
npx skills add inference-sh/skills@elevenlabs-tts

# ElevenLabs voice changer (transform recordings)
npx skills add inference-sh/skills@elevenlabs-voice-changer

# 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@infsh-cli

浏览音频应用：belt app list --category audio