tts-whatsapp

Safe
Speech & Transcription

Send high-quality text-to-speech voice messages on WhatsApp in 40+ languages with automatic delivery.

SKILL.md

# ๐ŸŽ™๏ธ TTS WhatsApp - Voice Messages in 40+ Languages Send high-quality text-to-speech voice messages on WhatsApp with automatic delivery. Supports 40+ languages, personal messages, and group broadcasts. ## โœจ Features - ๐ŸŽ™๏ธ **High-quality TTS** powered by Piper (40+ languages) - ๐ŸŽต **Automatic conversion** to OGG/Opus (WhatsApp format) - ๐Ÿ“ค **Automatic sending** via Clawdbot - ๐Ÿ‘ฅ **Group support** - Send to individuals or WhatsApp groups - ๐ŸŒ **Multi-language** - French, English, Spanish, German, and 40+ more - ๐Ÿงน **Smart cleanup** - Auto-delete files after successful send - โšก **Fast** - ~2-3s from command to delivery ## ๐Ÿ“ฆ Prerequisites 1. **Piper TTS**: `pip3 install --user piper-tts` 2. **FFmpeg**: `brew install ffmpeg` (macOS) or `apt install ffmpeg` (Linux) 3. **Voice models**: Download from [Hugging Face](https://huggingface.co/rhasspy/piper-voices) - Place in `~/.clawdbot/skills/piper-tts/models/` - Example: `fr_FR-siwis-medium.onnx` ## ๐Ÿš€ Quick Start ### Basic usage ```bash tts-whatsapp "Hello, this is a test" --target "+15555550123" ``` ### Send to WhatsApp group ```bash tts-whatsapp "Hello everyone" --target "120363257357161211@g.us" ``` ### Change language ```bash tts-whatsapp "Hola mundo" --lang es_ES --voice carlfm --target "+34..." ``` ### Different quality levels ```bash tts-whatsapp "High quality" --quality high --target "+1..." ``` ## ๐ŸŒ Supported Languages - ๐Ÿ‡ซ๐Ÿ‡ท French (`fr_FR`): siwis, upmc, tom - ๐Ÿ‡ฌ๐Ÿ‡ง English GB (`en_GB`): alan, alba - ๐Ÿ‡บ๐Ÿ‡ธ English US (`en_US`): lessac, amy, joe - ๐Ÿ‡ช๐Ÿ‡ธ Spanish (`es_ES`, `es_MX`): carlfm, davefx - ๐Ÿ‡ฉ๐Ÿ‡ช German (`de_DE`): thorsten, eva_k - ๐Ÿ‡ฎ๐Ÿ‡น Italian (`it_IT`): riccardo - ๐Ÿ‡ต๐Ÿ‡น Portuguese (`pt_BR`, `pt_PT`): faber - ๐Ÿ‡ณ๐Ÿ‡ฑ Dutch (`nl_NL`): mls, rdh - ๐Ÿ‡ท๐Ÿ‡บ Russian (`ru_RU`): dmitri, irina - And 30+ more! [Full voice list โ†’](https://rhasspy.github.io/piper-samples/) ## ๐Ÿ”ง Configuration Configure in `~/.clawdbot/clawdbot.json`: ```json { "skills": { "entries": { "tts_whatsapp": { "enabled": true, "env": { "WHATSAPP_DEFAULT_TARGET": "+15555550123", "PIPER_DEFAULT_LANG": "en_US", "PIPER_DEFAULT_VOICE": "lessac", "PIPER_DEFAULT_QUALITY": "medium" } } } } } ``` ## ๐ŸŽ›๏ธ All Options ``` --target NUMBER WhatsApp number or group ID --message TEXT Text message with audio --lang LANGUAGE Language (default: fr_FR) --voice VOICE Voice name (default: auto) --quality QUALITY x_low, low, medium, high --speed SPEED Playback speed (default: 1.0) --no-send Don't send automatically ``` ## ๐Ÿ“Š Performance ~2.3s total for a 10-second message: - TTS generation: ~1s - Format conversion: ~0.2s - WhatsApp delivery: ~1s ## ๐Ÿ“š Full Documentation See [README.md](README.md) for complete documentation, examples, and troubleshooting.

More in Speech & Transcription