omnivoice-tts — Claude Code skill: speech synthesis in 600+ languages
A skill for OmniVoice: clone a voice from a sample, generate speech from a text description, or run batch synthesis from Python and CLI.
npx skills add reason-machines/trending-skills --skill omnivoice-tts -a claude-codeWhat omnivoice-tts does
OmniVoice is a zero-shot TTS model covering 600+ languages. The skill hands your agent ready recipes: loading the model with OmniVoice.from_pretrained, cloning a voice from ref_audio and ref_text, designing a voice through an instruct string, or letting the model pick one. Generation parameters include num_step, speed and duration, and non-verbal tags like [laughter] go straight into the text.
Setup covers pip install omnivoice or a source install, plus three CLI tools: omnivoice-demo for a web demo, omnivoice-infer for a single run, and omnivoice-infer-batch for JSONL-driven batches. In the batch file only id and text are required; reference audio, instruct and language fields are optional.
Check your environment first. Python 3.9+ and PyTorch 2.8+ are required, with CUDA, Apple Silicon MPS or CPU as device options — CPU is the slow path. If HuggingFace is unreachable, the skill suggests pointing HF_ENDPOINT at a mirror. A mismatched torch version is the usual reason the model fails to load, so verify that before anything else.
What it helps with
- clone a speaker from a short reference clip
- generate a voice from written attributes with no recording
- run batch synthesis across a JSONL list on multiple GPUs
- control speaking rate or pin the output duration
- drop laughter or sighs into the synthesized line
Example prompts for the agent
- Clone the voice from
ref.wavand read the line "Synthesis check" - Generate the line with a female, low pitch, british accent voice
- Run batch inference on
test.jsonland write results toresults/
How to install omnivoice-tts
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill omnivoice-tts -a claude-code2Manually: put the files in place
~/.claude/skills/omnivoice-tts/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/omnivoice-tts/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill omnivoice-tts -a codex2Manually: put the files in place
.agents/skills/omnivoice-tts/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill omnivoice-tts -a cursor2Manually: put the files in place
.cursor/skills/omnivoice-tts/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install reason-machines/trending-skills omnivoice-tts2Manually: put the files in place
.github/skills/omnivoice-tts/SKILL.md1Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill omnivoice-tts -a gemini-cli2Platform CLI
gemini skills install https://github.com/reason-machines/trending-skills --path skills/omnivoice-ttsManually: put the files in place
.devin/skills/omnivoice-tts/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add reason-machines/trending-skills --skill omnivoice-tts -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about omnivoice-tts
How do I install omnivoice-tts in Claude?
Run npx skills add reason-machines/trending-skills --skill omnivoice-tts -a claude-code. The skill lands at ~/.claude/skills/omnivoice-tts/SKILL.md.
What does omnivoice-tts do?
It gives the agent instructions for OmniVoice: voice cloning, voice design, auto voice, batch inference and the CLI tools.
What do I need to run OmniVoice?
Python 3.9+ and PyTorch 2.8+. Acceleration works on CUDA or Apple Silicon via MPS; CPU runs too, just slower.
