Клонирование голоса и синтез речи через TTS

★ 7.7 · content

ai-voice-cloning is a Claude Code skill that generates speech via the inference.sh CLI across multiple TTS models: Inworld TTS-2, Inworld TTS 1.5 (Max and Mini), ElevenLabs, Kokoro, DIA, Chatterbox, Higgs, and VibeVoice. Inworld TTS-2 covers 100+ languages with emotion and delivery steering through inline tags like `[excited]`, `[whisper]`, and `[gasp]`, backed by 271+ built-in voices; the TTS 1.5 Mini variant delivers ultra-low latency (~120 ms) for real-time conversational AI. ElevenLabs provides 22+ premium voices across 32 languages plus a voice-changer mode for transforming existing recordings. The skill fits voiceovers, audiobooks, podcasts, gaming NPCs, avatar audio, and accessibility use cases where natural or expressive synthetic speech is required.