Convert text to natural speech with Inworld TTS, ElevenLabs, DIA TTS, Kokoro, Chatterbox, and more via inference.sh CLI. Models: Inworld TTS-2 (100+ languages, emotion steering), Inworld TTS 1.5 (ultra-low latency), ElevenLabs (premium, 22+ voices, 32 languages), DIA TTS (conversational), Kokoro TTS, Chatterbox, Higgs Audio, VibeVoice (podcasts).
安装
npx skills add inference-sh/skills --skill text-to-speechnpx skills add inference-sh/skills --skill text-to-speech -a claude-code -gnpx skills add inference-sh/skills --skill text-to-speech -a codex -ggemini skills install https://github.com/inference-sh/skills.git --path tools/audio/text-to-speechgh skill install inference-sh/skills text-to-speechgit clone --depth 1 https://github.com/inference-sh/skills /tmp/inference-sh__skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/inference-sh__skills/tools/audio/text-to-speech ~/.claude/skills/text-to-speech # Claude Code
cp -R /tmp/inference-sh__skills/tools/audio/text-to-speech ~/.agents/skills/text-to-speech # Codex, Cursor, Gemini CLI, Copilot, OpenCode