voice
The voice skill converts text to speech audio by executing the `mb voice` CLI command, generating MP3 files from provided text. Use it when users request audio generation, ask you to speak or read aloud, or want voice recordings of text content, with support for multiple TTS providers including Edge TTS, OpenAI, ElevenLabs, and Doubao with configurable voices and output options.
git clone --depth 1 https://github.com/xvirobotics/metabot /tmp/voice && cp -r /tmp/voice/src/skills/voice ~/.claude/skills/voiceSKILL.md
## Text-to-Speech (Voice Output) Generate MP3 audio from text using the `mb voice` CLI. ### Quick Commands ```bash # Generate MP3, prints file path to stdout mb voice "Hello, this is a test" # Generate and play immediately mb voice "Hello" --play # Save to specific file mb voice "Hello" -o greeting.mp3 # Override provider and voice mb voice "Hello" --provider doubao --voice zh_female_wanqudashu_moon_bigtts # Pipe text (useful for long content) echo "Long text here" | mb voice echo "Long text" | mb voice -o output.mp3 ``` ### When to Use - User asks you to "say", "speak", "read aloud", or "generate audio/voice" - User wants a voice recording or audio version of text - User requests TTS (text-to-speech) output ### Available Providers & Voices **Edge TTS (default, free, no key needed):** - `zh-CN-XiaoyiNeural` (default) — Female Chinese - `zh-CN-YunxiNeural` — Male Chinese - `zh-CN-XiaoxiaoNeural` — Female Chinese - `en-US-JennyNeural` — Female English **Doubao (default when Volcengine keys configured):** - `zh_female_wanqudashu_moon_bigtts` (default) — Female Chinese - Other Volcengine voice IDs from the TTS console **OpenAI (when OPENAI_API_KEY set):** - `alloy` (default), `echo`, `fable`, `onyx`, `nova`, `shimmer` **ElevenLabs (when ELEVENLABS_API_KEY set):** - Voice IDs from the ElevenLabs console ### Text Limits - Doubao: ~300 Chinese characters (longer text is auto-truncated) - OpenAI / ElevenLabs / Edge: ~4000 characters ### Guidelines - For short text (greetings, alerts), use inline: `mb voice "text"` - For longer text, pipe through stdin: `echo "..." | mb voice` - The output file is MP3 format - Use `--play` only when the user explicitly wants to hear the audio (it blocks until playback completes) - When saving files for the user, use `-o` with a descriptive filename - To send the audio to the user in Feishu, copy the file to the outputs directory: `cp /tmp/mb-voice-xxx.mp3 /tmp/metabot-outputs/<chatId>/`
Generate high-quality speech audio using Doubao (豆包/Volcengine) TTS API. Use this skill when the user asks to generate audio, podcasts, voiceovers, or text-to-speech output.
Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
Read and write shared memory documents. Use this when you need to save knowledge, notes, research findings, or project context for future reference across sessions. Also use it to look up previously stored information.
Talk to other MetaBot bots (`mb talk` — send a message to another bot, including cross-instance peers). Use when you want to delegate to or message another bot, e.g. 'talk to bot X', '跟其他 bot 说话', 'send message to peer bot', 'ask the deploy-bot', 'delegate to bot'. Also covers bot/peer management, skill hub, voice calls.
MetaBot's persistent server-side scheduler (cron + one-shot). Optional skill — not installed by default. Use when the user wants tasks that survive Claude session restarts, are visible to other bots, or need to run in MetaBot's PM2 process rather than this Claude session.
The meta-skill: create AI agent teams, individual agents, or custom skills for any project. Use when the user wants to generate a complete agent team, create a single agent, or create a single skill for Claude Code, Kimi, or Codex.