An offline text-to-speech toolkit that turns written text into spoken audio. It can use a short voice recording to imitate a voice, or create a voice from described attributes, across many languages.

Use it to create multilingual speech, clone a voice from a short recording, design a voice from traits, or generate speech without a reference voice.

It lets speech generation run on supported local hardware instead of requiring a cloud speech service. It also provides one workflow for narration, designed voices, and voice imitation.

omnivoice — Skill for Claude Code by oyi77/1ai-skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add oyi77/1ai-skills --skill omnivoice

Clone the repo

git clone --depth 1 https://github.com/oyi77/1ai-skills

Made for: Claude Code.

Or install 1ai-skills, the plugin that ships this one along with the rest of its 240 skills, 4 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/oyi77/1ai-skills/omnivoice/github.svg)](https://agentmods.dev/skills/oyi77/1ai-skills/omnivoice)

Your own site

<a href="https://agentmods.dev/skills/oyi77/1ai-skills/omnivoice"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/omnivoice/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/oyi77/1ai-skills/omnivoice"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/omnivoice.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,386 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00033	$0.01386
Opus 5.5	$0.00013	$0.00554
Sonnet 5.5	$0.00007	$0.00277
Haiku 4.5	$0.00003	$0.00139

Measured today against content hash 4d39c73f254c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

omnivoice scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

content/voice/omnivoice/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OmniVoice Skill

Overview

OmniVoice (k2-fsa/OmniVoice, Apache-2.0, README read 2026-11-05) is an offline-capable zero-shot text-to-speech toolkit built on a diffusion language-model-style architecture supporting 600+ languages. One pretrained checkpoint (k2-fsa/OmniVoice) serves three generation modes through the same model.generate() call: voice cloning from 3-10 seconds of reference audio (ref_audio plus optional ref_text, auto-transcribed via Whisper when omitted), voice design from a comma-separated attribute string (instruct="female, low pitch, british accent", no reference audio), and auto voice with no prompt at all. Output is a list of np.ndarray at 24 kHz. It runs on NVIDIA CUDA, Apple Silicon mps, Intel Arc xpu, and CPU, with streaming-style low real-time factor, non-verbal tags ([laughter], [sigh]), pinyin tone and CMU-dict pronunciation control, and three CLI entry points (omnivoice-demo Gradio web UI, omnivoice-infer single item, omnivoice-infer-batch multi-GPU batch).

When to Use

Trigger phrases:

"omnivoice voice cloning"
"omnivoice-infer"
"zero-shot TTS offline"
"voice design instruct"

Use cases:

Short-form narration cloned from a 3-10 second reference clip
Multilingual dubbing where the reference and target share a language
Voice prototyping from attribute descriptions with no reference audio

When NOT to Use

Cloning a voice without the speaker's consent — the upstream disclaimer prohibits unauthorized voice cloning, impersonation, fraud, and scams; voice data is biometric data under regimes such as GDPR and BIPA.
Expecting accent-free cross-lingual cloning — when reference audio and target speech differ in language, output carries the reference language's accent.
Reference clips far outside 3-10 seconds — longer audio slows inference and may degrade cloning quality.
Very short clips (1-2 seconds) with no reference audio — the model does not reliably generate them; provide reference audio.
Voice design outside Chinese and English — the model is trained on voice cloning primarily and voice design on Chinese and English only, so other languages may be unstable.
Trusting raw numerals — pass normalize_text=True (requires pip install "omnivoice[tn]") or expand "123" to words yourself.

Read the full file on GitHub · 100 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed · +2 lines 4d39c73f254c
2d ago First seen · 98 lines · 33 tokens per session scan A 7d6c2d0cebbd

Subscribe to this mod's changes

omnivoice is a skill published in the GitHub repository oyi77/1ai-skills (17 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 1,386 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-06.

Creative and media Multilingual agent ai-agent ai-automation ai-skills automation content diffusion offline speech-synthesis tts voice-cloning

omnivoice next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
omnivoiceoyi77/1ai-skills	Skill	17	yesterday	MIT	A	33	Claude Code
skillpack-creatorCreminiAI/skillpack	Skill	1.2k	1mo ago	MIT	A	67	Codex
create-supervisorUniversePeak/Supervisor.skill	Skill	54	2d ago	MIT	A	81	Codex
wechat-sticker-assets-designerguanyang/super-publisher	Skill	35	26d ago	MIT	A	56	Claude Code
sticker-factoryguanyang/super-publisher	Skill	35	26d ago	MIT	A	65	Claude Code
content-writerEvovexAI/EvoFlow	Skill	606	yesterday	none	A	45	Claude Code, Codex
amazon-qbusiness-anonymous-mcpFriz-zy/ai-capability-registry	Skill	12	1mo ago	MIT	A	18	Claude Code, Codex