Generate local text-to-speech with voice cloning and batch dubbing.
npx skills add https://github.com/mu-zi-lee/qwen3-tts-skill --skill qwen3-tts-skills
Please help me install this Agent Skill. Skill: qwen3-tts-skills Source: https://github.com/mu-zi-lee/qwen3-tts-skill/tree/main Command: npx skills add https://github.com/mu-zi-lee/qwen3-tts-skill --skill qwen3-tts-skills
This Skill eliminates the need for manual, cloud-dependent text-to-speech workflows, enabling local, high-quality speech generation for diverse content creation tasks without recurring API costs or privacy concerns.
Use the qwen3-tts-skills skill to generate a 1-minute Chinese audiobook segment with a natural female voice, or clone a reference audio to narrate your entire blog post with consistent tone.
High-intent search queries and answers about installing and using this skill.
Local text-to-speech generation without cloud APIs is achieved by running inference directly on your machine using configurable performance parameters. This eliminates recurring API costs and privacy concerns while supporting video voiceover and audiobook production.
Voice cloning from reference audio supports multi-role dialogue narration and personalized voice design. You can use natural language prompts to design voices or clone audio references to narrate long-form content with consistent tone.
Batch dubbing for long-form audiobooks automates converting articles or video scripts into merged audio files. It supports configurable silence gaps, segment-level emotion control, and FFmpeg merging for the final output.
Local TTS inference with Torch supports built-in speakers and emotion control through the CustomVoice mode. This allows configurable performance parameters for generating natural speech locally without external services.
FFmpeg is required for merging audio segments during batch text-to-speech workflows. The process automates merging individual speech segments into full audio files with configurable silence gaps between dialogues.
Local speech generation avoids third-party text-to-speech services to eliminate recurring API costs and privacy concerns. It enables high-quality, customizable voice generation for video voiceovers and audiobook production directly on your infrastructure.
zeronx798Transcribe multilingual audio files into text using OpenAI's Whisper model.
dkyazzentwatwaSplit audio files into segments by detecting silence gaps with pydub.
missyouangeledConvert text into speech audio using Kokoro offline or Noiz cloud backends.
AG064Convert input text to speech offline using sherpa-onnx runtime.
