omnivoice

Local TTS, voice cloning, voice design, and video dubbing via the VoiceStudio MCP server (open-source ElevenLabs alternative; nothing leaves the machine, runs on MPS/CUDA/CPU). Use when: (1) generating speech from text in any of 646 languages, (2) cloning a voice from a 3-second reference clip, (3) designing a voice by gender/age/accent/pitch/style, (4) dubbing a video into another language, (5) listing voice profiles or personality presets, (6) producing narration where privacy, cost, or absent API keys matter, (7) non-English narration where Edge TTS/kokoro fall short, (8) batch audio for blog posts or content pipelines. Triggers: 'omnivoice', 'voice clone', 'clone this voice', 'tts', 'narrate', 'generate speech', 'voice synthesis', 'dub video', 'voice design', 'local tts', 'multilingual voice', 'narrate this post', 'elevenlabs alternative'.

Install

npx skills add 'https://github.com/debpalash/VoiceStudio/tree/main/.claude/skills/omnivoice'

Download bundle ↓

main · 4e55180 ↗Scanned 2026-09-15

scripts/check-health.shBrowse 7 files

90 tokens

236 bytes
Token encoding: o200k_base
Snapshot 4e55180

← Back to SKILL.md

1#!/usr/bin/env bash2set -euo pipefail3URL="${OMNIVOICE_API_URL:-http://127.0.0.1:3900}/health"4if out=$(curl -sf --max-time 3 "$URL" 2>/dev/null); then5  echo "$out"6  exit 07fi8echo "omnivoice backend not reachable at $URL" >&29exit 110

Referenced from SKILL.md

SKILL.mdView in source ↗

28```bash29scripts/check-health.sh        # exit 0 if up30scripts/start-backend.sh       # boot in background (MPS/CUDA auto-detected)

SKILL.mdView in source ↗

164- [references/mcp-setup.md](references/mcp-setup.md) — MCP wiring, backend lifecycle, env vars, troubleshooting165- [scripts/check-health.sh](scripts/check-health.sh) — `curl /health`, exit 0/1166- [scripts/start-backend.sh](scripts/start-backend.sh) — Start uvicorn on 127.0.0.1:3900 with health probe

← All VoiceStudio skills Project instructions →