闲社服务运行正常AI智能体自动化平台
客户端下载帮助中心服务商入驻
免费注册
技能集市 > AI智能 > text-to-speech
t

文本转语音

技能标识：text-to-speech

Convert text to natural speech with DIA TTS, Kokoro, Chatterbox, and more via inference.sh CLI. Models: DIA TTS (conversational), Kokoro TTS, Chatterbox, Higgs Audio, VibeVoice (podcasts). Capabilities: text-to-speech, voice cloning, multi-speaker dialogue, podcast generation, expressive speech. Use for: voiceovers, audiobooks, podcasts, accessibility, video narration, IVR, voice assistants. Triggers: text to speech, tts, voice generation, ai voice, speech synthesis, voice over, generate speech,

作者：admin | 来源记录：ClawHub
下载
登记来源
ClawHub
版本
V 0.1.5
检测标记
后台标记通过
免费
免费获取
0
收藏
来源与检测标记为平台登记信息，并不代表已展示可复核的检测报告。使用前请核对版本、依赖和所需权限，建议先在隔离环境中运行。
概述
安装方式
版本历史

文本转语音

文本转语音

通过 inference.sh 命令行工具将文本转换为自然语音。

文本转语音

快速开始

bash

安装命令行工具


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

生成语音

infsh app run infsh/kokoro-tts --input {text: 你好，欢迎来到我们的产品演示。}

安装说明： 安装脚本仅检测您的操作系统/架构，从 dist.inference.sh 下载匹配的二进制文件，并验证其 SHA-256 校验和。无需提升权限或后台进程。提供手动安装与验证。

可用模型

模型应用 ID最佳用途
DIA TTSinfsh/dia-tts对话式、富有表现力
Kokoro TTS
infsh/kokoro-tts | 快速、自然 | | Chatterbox | infsh/chatterbox | 通用 | | Higgs Audio | infsh/higgs-audio | 情感控制 | | VibeVoice | infsh/vibevoice | 播客、长文本 |

浏览所有音频应用

bash
infsh app list --category audio

示例

基础文本转语音

bash
infsh app run infsh/kokoro-tts --input {text: 欢迎来到我们的教程。}

使用 DIA 的对话式 TTS

bash
infsh app sample infsh/dia-tts --save input.json

编辑 input.json：

{

text: 嘿！你今天过得怎么样？我真的很兴奋能和你分享这个。,

voice: conversational

}

infsh app run infsh/dia-tts --input input.json

长文本音频（播客）

bash
infsh app sample infsh/vibevoice --save input.json

用您的播客脚本编辑 input.json

infsh app run infsh/vibevoice --input input.json

使用 Higgs 的情感化语音

bash
infsh app sample infsh/higgs-audio --save input.json

{

text: 这简直太不可思议了！,

emotion: excited

}

infsh app run infsh/higgs-audio --input input.json

使用场景

  • - 配音：产品演示、解说视频
  • 有声书：将文本转换为语音
  • 播客：生成播客节目
  • 无障碍：让内容更易访问
  • IVR：电话系统语音提示
  • 视频旁白：为视频添加旁白

与视频结合

生成语音，然后创建虚拟人物视频：

bash

1. 生成语音


infsh app run infsh/kokoro-tts --input {text: 您的脚本内容} > speech.json

2. 使用音频 URL 与 OmniHuman 创建虚拟形象视频

infsh app run bytedance/omnihuman-1-5 --input { image_url: https://portrait.jpg, audio_url: <步骤1中的音频URL> }

相关技能

bash

完整平台技能（150+ 应用）


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

AI 虚拟形象（结合 TTS 与虚拟人物）

npx skills add inference-sh/skills@ai-avatar-video

AI 音乐生成

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

语音转文本（转录）

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

视频生成

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

浏览所有应用：infsh app list

文档

标签

skill ai

通过对话安装

以下为平台配置的接入选项，并非逐项实测通过。能否安装取决于客户端支持、技能来源和运行环境：

OpenClaw WorkBuddy QClaw Kimi Claude

方式一：安装 SkillHub 和技能

帮我安装 SkillHub 和 text-to-speech-1776274668 技能

方式二：设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源，然后帮我安装 text-to-speech-1776274668 技能

通过命令行安装

skillhub install text-to-speech-1776274668

下载

⬇ 下载 text-to-speech v0.1.5（免费）

文件大小: 2.3 KB | 发布时间: 2026-4-16 17:01

v0.1.5 最新 2026-4-16 17:01
- Added detailed feature descriptions, available models, and example commands for using text-to-speech with inference.sh CLI.
- Expanded documentation to cover advanced options like voice cloning, expressive speech, podcast generation, and conversational TTS.
- Introduced installation notes and security overview for the CLI install script.
- Included use cases and guidance for combining speech with AI avatar video generation.
- Listed related skills and resources for broader AI audio/video workflows.

相关推荐

s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
s

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

AI智能
返回顶部