unsloth-tts
Unsloth-tts brings the library's performance optimizations to speech synthesis models. Specifically optimized for the Llama-based Orpheus-TTS architecture, it enables high-quality voice cloning with 50% less memory than standard implementations.
npx skills add majiayu000/claude-skill-registry --skill unsloth-tts --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
--- name: unsloth-tts description: Fine-tuning Text-to-Speech (TTS) models with Unsloth for voice cloning and synthetic speech (triggers: TTS, text-to-speech, voice cloning, Orpheus-TTS, audio fine-tuning, speech synthesis). --- ## Overview Unsloth-tts brings the library's performance optimizations to speech synthesis models. Specifically optimized for the Llama-based Orpheus-TTS architecture, it enables high-quality voice cloning with 50% less memory than standard implementations. ## When to Use - When creating custom voice clones that require realistic phrasing and emotional quirks. - When fine-tuning Orpheus-TTS for specialized synthesis (e.g., laughter, sighs). - When deploying TTS models via llama.cpp or GGUF. ## Decision Tree 1. Is high audio quality the priority over VRAM? - Yes: Load with `load_in_4bit = False`. 2. Does the target voice have specific quirks (e.g., laughter)? - Yes: Annotate transcripts with emotion tags like `<laughs>`. 3. Is this a quick test or full replication? - Quick test: Set `max_steps = 60`. - Full replication: Train for 1 full epoch with 1-3 hours of data. ## Workflows 1. **Voice Cloning with LoRA**: Load `orpheus-3b-0.1-pretrained`, prepare 1-3 ho
- Overview
- When to Use
- Decision Tree
- Workflows
- Non-Obvious Insights
- Evidence
- Scripts
- Dependencies
- References
What does the unsloth-tts skill do?
Unsloth-tts brings the library's performance optimizations to speech synthesis models. Specifically optimized for the Llama-based Orpheus-TTS architecture, it enables high-quality voice cloning with 50% less memory than standard implementations.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill unsloth-tts --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.