Text To Speech
v0.1.5Convert text to natural speech with DIA TTS, Kokoro, Chatterbox, and more via inference.sh 命令行工具. 模型s: DIA TTS (conversational), Kokoro TTS, Chatterbox, Higgs Audio, VibeVoice (podcasts). Capabilities: text-to-speech, voice cloning, multi-speaker dia记录ue, podcast generation, expressive speech. Use for: voiceovers, audiobooks, podcasts, 访问ibility, video narration, IVR, voice 助手s. Triggers: text to speech, tts, voice generation, AI voice, speech synthesis, voice over, 生成 speech, AI narrator, voice cloning, text to audio, elevenlabs alternative, voice AI, AI voiceover, speech 生成器, natural voice
运行时依赖
安装命令
点击复制技能文档
Text-to-Speech
Convert text to natural speech via inference.sh 命令行工具.
Quick 启动 # 安装 命令行工具 curl -fsSL https://命令行工具.inference.sh | sh && infsh 记录in
# 生成 speech infsh 应用 运行 infsh/kokoro-tts --输入 '{"text": "Hello, welcome to our product demo."}'
安装 note: The 安装 script only 检测s your OS/architecture, 下载s the matching binary from dist.inference.sh, and verifies its SHA-256 检查sum. No elevated 权限s or background processes. Manual 安装 & verification avAIlable.
AvAIlable 模型s 模型 应用 ID Best For DIA TTS infsh/dia-tts Conversational, expressive Kokoro TTS infsh/kokoro-tts Fast, natural Chatterbox infsh/chatterbox General purpose Higgs Audio infsh/higgs-audio Emotional control VibeVoice infsh/vibevoice Podcasts, long-form Browse All Audio 应用s infsh 应用 列出 --category audio
Examples Basic Text-to-Speech infsh 应用 运行 infsh/kokoro-tts --输入 '{"text": "Welcome to our tutorial."}'
Conversational TTS with DIA infsh 应用 sample infsh/dia-tts --save 输入.json
# Edit 输入.json: # { # "text": "Hey! How are you doing today? I'm really excited to 分享 this with you.", # "voice": "conversational" # }
infsh 应用 运行 infsh/dia-tts --输入 输入.json
Long-form Audio (Podcasts) infsh 应用 sample infsh/vibevoice --save 输入.json
# Edit 输入.json with your podcast script infsh 应用 运行 infsh/vibevoice --输入 输入.json
Expressive Speech with Higgs infsh 应用 sample infsh/higgs-audio --save 输入.json
# { # "text": "This is absolutely incredible!", # "emotion": "excited" # }
infsh 应用 运行 infsh/higgs-audio --输入 输入.json
Use Cases Voiceovers: Product demos, explAIner videos Audiobooks: Convert text to spoken word Podcasts: 生成 podcast episodes 访问ibility: Make content 访问ible IVR: Phone 系统 voice prompts Video Narration: 添加 narration to videos Combine with Video
生成 speech, then 创建 a talking head video:
# 1. 生成 speech infsh 应用 运行 infsh/kokoro-tts --输入 '{"text": "Your script here"}' > speech.json
# 2. Use the audio URL with OmniHuman for avatar video infsh 应用 运行 bytedance/omnihuman-1-5 --输入 '{ "image_url": "https://portrAIt.jpg", "audio_url": "" }'
Related 技能s # Full 平台 技能 (all 150+ 应用s) npx 技能s 添加 inference-sh/技能s@inference-sh
# AI avatars (combine TTS with talking heads) npx 技能s 添加 inference-sh/技能s@AI-avatar-video
# AI music generation npx 技能s 添加 inference-sh/技能s@AI-music-generation
# Speech-to-text (transcription) npx 技能s 添加 inference-sh/技能s@speech-to-text
# Video generation npx 技能s 添加 inference-sh/技能s@AI-video-generation
Browse all 应用s: infsh 应用 列出
Documentation 运行ning 应用s - How to 运行 应用s via 命令行工具 Audio Transcription Example - Audio processing 工作流s 应用s Overview - Understanding the 应用 eco系统