{"skill":{"slug":"clonev","displayName":"Clonev","summary":"Clone any voice and generate speech using Coqui XTTS v2. SUPER SIMPLE - provide a voice sample (6-30 sec WAV) and text, get cloned voice audio. Supports 14+ languages. Use when the user wants to (1) Clone their voice or someone else's voice, (2) Generate speech that sounds like a specific person, (3) Create personalized voice messages, (4) Multi-lingual voice cloning (speak any language with cloned voice).","description":"---\nname: clonev\ndescription: Clone any voice and generate speech using Coqui XTTS v2. SUPER SIMPLE - provide a voice sample (6-30 sec WAV) and text, get cloned voice audio. Supports 14+ languages. Use when the user wants to (1) Clone their voice or someone else's voice, (2) Generate speech that sounds like a specific person, (3) Create personalized voice messages, (4) Multi-lingual voice cloning (speak any language with cloned voice).\n---\n\n# CloneV Skill - Voice Cloning Made Simple\n\n## ⚠️ CRITICAL INSTRUCTIONS FOR AI MODELS\n\n**DO NOT** try to use Docker containers directly.\n**DO NOT** try to interact with `coqui-xtts` container - it is broken and restarting.\n**DO NOT** try to use APIs or servers.\n\n**ONLY USE THE SCRIPT:** `scripts/clonev.sh`\n\nThe script handles everything automatically. Just call it with text, voice sample, and language.\n\n---\n\n## What This Skill Does\n\nClones any voice from a short audio sample and generates new speech in that voice.\n\n**Input**: \n- Text to speak\n- Voice sample (WAV file, 6-30 seconds)\n- Language code\n\n**Output**: OGG voice file (cloned voice speaking the text)\n\n**Works with**: Any voice! Yours, a celebrity, a character, etc.\n\n---\n\n## The ONE Command You Need\n\n```bash\n$(scripts/clonev.sh \"Your text here\" /path/to/voice_sample.wav language)\n```\n\nThat's it! Nothing else needed.\n\n---\n\n## Step-by-Step Usage (FOR AI MODELS)\n\n### Step 1: Get the required inputs\n- Text to speak (from user)\n- Path to voice sample WAV file (from user)\n- Language code (from user or default to `en`)\n\n### Step 2: Run the script\n```bash\nVOICE_FILE=$(scripts/clonev.sh \"TEXT_HERE\" \"/path/to/sample.wav\" LANGUAGE)\n```\n\n### Step 3: Use the output\nThe variable `$VOICE_FILE` now contains the path to the generated OGG file.\n\n---\n\n## Complete Working Examples\n\n### Example 1: Clone voice and send to Telegram\n```bash\n# Generate cloned voice\nVOICE=$(/home/bernie/clawd/skills/clonev/scripts/clonev.sh \"Hello, this is my cloned voice!\" \"/mnt/c/TEMP/Recording 25.wav\" en)\n\n# Send to Telegram (as voice message)\nmessage action=send channel=telegram asVoice=true filePath=\"$VOICE\"\n```\n\n### Example 2: Clone voice in Czech\n```bash\n# Generate Czech voice\nVOICE=$(/home/bernie/clawd/skills/clonev/scripts/clonev.sh \"Ahoj, tohle je můj hlas\" \"/mnt/c/TEMP/Recording 25.wav\" cs)\n\n# Send\nmessage action=send channel=telegram asVoice=true filePath=\"$VOICE\"\n```\n\n### Example 3: Full workflow with check\n```bash\n#!/bin/bash\n\n# Generate voice\nVOICE=$(/home/bernie/clawd/skills/clonev/scripts/clonev.sh \"Task completed!\" \"/path/to/sample.wav\" en)\n\n# Verify file was created\nif [ -f \"$VOICE\" ]; then\n    echo \"Success! Voice file: $VOICE\"\n    ls -lh \"$VOICE\"\nelse\n    echo \"Error: Voice file not created\"\nfi\n```\n\n---\n\n## Common Language Codes\n\n| Code | Language | Example Usage |\n|------|----------|---------------|\n| `en` | English | `scripts/clonev.sh \"Hello\" sample.wav en` |\n| `cs` | Czech | `scripts/clonev.sh \"Ahoj\" sample.wav cs` |\n| `de` | German | `scripts/clonev.sh \"Hallo\" sample.wav de` |\n| `fr` | French | `scripts/clonev.sh \"Bonjour\" sample.wav fr` |\n| `es` | Spanish | `scripts/clonev.sh \"Hola\" sample.wav es` |\n\nFull list: en, cs, de, fr, es, it, pl, pt, tr, ru, nl, ar, zh, ja, hu, ko\n\n---\n\n## Voice Sample Requirements\n\n- **Format**: WAV file\n- **Length**: 6-30 seconds (optimal: 10-15 seconds)\n- **Quality**: Clear audio, no background noise\n- **Content**: Any speech (the actual words don't matter)\n\n**Good samples**:\n- ✅ Recording of someone speaking clearly\n- ✅ No music or noise in background\n- ✅ Consistent volume\n\n**Bad samples**:\n- ❌ Music or songs\n- ❌ Heavy background noise\n- ❌ Very short (< 6 seconds)\n- ❌ Very long (> 30 seconds)\n\n---\n\n## ⚠️ Important Notes\n\n### Model Download\n- First use downloads ~1.87GB model (one-time)\n- Model is stored at: `/mnt/c/TEMP/Docker-containers/coqui-tts/models-xtts/`\n- Status: ✅ Already downloaded\n\n### Processing Time\n- Takes 20-40 seconds depending on text length\n- This is normal - voice cloning is computationally intensive\n\n---\n\n## Troubleshooting\n\n### \"Command not found\"\nMake sure you're in the skill directory or use full path:\n```bash\n/home/bernie/clawd/skills/clonev/scripts/clonev.sh \"text\" sample.wav en\n```\n\n### \"Voice sample not found\"\n- Check the path to the WAV file\n- Use absolute paths (starting with `/`)\n- Ensure file exists: `ls -la /path/to/sample.wav`\n\n### \"Model not found\"\nThe model should auto-download. If not:\n```bash\ncd /mnt/c/TEMP/Docker-containers/coqui-tts\ndocker run --rm --entrypoint \"\" \\\n  -v $(pwd)/models-xtts:/root/.local/share/tts \\\n  ghcr.io/coqui-ai/tts:latest \\\n  python3 -c \"from TTS.api import TTS; TTS('tts_models/multilingual/multi-dataset/xtts_v2')\"\n```\n\n### Poor voice quality\n- Use clearer voice sample\n- Ensure no background noise\n- Try different sample (some voices clone better)\n\n---\n\n## Quick Reference Card (FOR AI MODELS)\n\n```\nUSER: \"Clone my voice and say 'hello'\"\n→ Get: sample path, text=\"hello\", language=\"en\"\n→ Run: VOICE=$(/home/bernie/clawd/skills/clonev/scripts/clonev.sh \"hello\" \"/path/to/sample.wav\" en)\n→ Result: $VOICE contains path to OGG file\n→ Send: message action=send channel=telegram asVoice=true filePath=\"$VOICE\"\n```\n\n```\nUSER: \"Make me speak Czech\"\n→ Get: sample path, text=\"Ahoj\", language=\"cs\"  \n→ Run: VOICE=$(/home/bernie/clawd/skills/clonev/scripts/clonev.sh \"Ahoj\" \"/path/to/sample.wav\" cs)\n→ Send: message action=send channel=telegram asVoice=true filePath=\"$VOICE\"\n```\n\n---\n\n## Output Location\n\nGenerated files are saved to:\n```\n/mnt/c/TEMP/Docker-containers/coqui-tts/output/clonev_output.ogg\n```\n\nThe script returns this path, so you can use it directly.\n\n---\n\n## Summary\n\n1. **ONLY use the script**: `scripts/clonev.sh`\n2. **NEVER** try to use Docker containers directly\n3. **NEVER** try to interact with the `coqui-xtts` container\n4. Script handles everything automatically\n5. Returns path to OGG file ready to send\n\n**Simple. Just use the script.**\n\n---\n\n*Clone any voice. Speak any language. Just use the script.*\n","topics":["Audio"],"tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":2719,"installsAllTime":102,"installsCurrent":6,"stars":0,"versions":1},"createdAt":1770219757606,"updatedAt":1779076662616},"latestVersion":{"version":"1.0.0","createdAt":1770219757606,"changelog":"Initial release of CloneV skill – voice cloning made simple.\n\n- Provides a one-command solution for cloning any voice and generating speech using Coqui XTTS v2.\n- Supports 14+ languages; easily specify language code for multi-lingual speech.\n- Requires a 6–30 second WAV voice sample and text; outputs an OGG file with cloned voice.\n- Strict instructions: use only the included `scripts/clonev.sh` script (no direct Docker/API use).\n- Detailed usage, troubleshooting, and reference provided in SKILL.md for quick, efficient deployment.","license":null},"metadata":null,"owner":{"handle":"instant-picture","userId":"s17eq24k1a2bd4ar0k70yhyreh8853wk","displayName":"instant-picture","image":"https://avatars.githubusercontent.com/u/27382780?v=4"},"moderation":{"isSuspicious":false,"isMalwareBlocked":false,"verdict":"clean","reasonCodes":["review.llm_review"],"summary":"Review: review.llm_review","engineVersion":"v2.4.24","updatedAt":1779947654274}}