Manage and switch TTS voices across Piper TTS and macOS Say via slash commands.
npx skills add https://github.com/paulpreibisch/AgentVibes --skill agentvibes
Please help me install this Agent Skill. Skill: agentvibes Source: https://github.com/paulpreibisch/AgentVibes/tree/main/.clawdbot/skill Command: npx skills add https://github.com/paulpreibisch/AgentVibes --skill agentvibes
AgentVibes Voice Management reduces friction of handling multiple TTS providers by centralizing voice discovery, switching, and preview tasks.
Switch to a preferred voice using /agent-vibes:switch and verify with /agent-vibes:get.
High-intent search queries and answers about installing and using this skill.
To preview TTS voices before switching, use the built-in voice preview functionality to audition audio samples. This lets you quickly listen to available voices across Piper TTS and macOS Say, ensuring you select the preferred expressive speech output.
Yes, you can add custom Piper TTS voices to your local library. The Skill supports local voice configuration, allowing you to expand your available voice options beyond the default presets for more diverse text-to-speech synthesis.
The best way to list available TTS voices across different providers is through the structured command surface. It provides deterministic behavior for voice discovery, centralizing all available options from both Piper TTS and macOS Say into a single view.
Yes, TTS voice management works without external dependencies. The Skill operates independently to manage local voice configuration and provider switching, ensuring consistent, expressive speech in Claude sessions without requiring additional packages.
Text-to-speech voice switching may not apply if the provider transition was not verified. After using /agent-vibes:switch, confirm the active voice with /agent-vibes:get to ensure the local configuration properly registered the real-time voice change.
michaelboedingConvert text into speech using Gemini, ElevenLabs, or OpenAI TTS backends.
adiytharpansaConvert written text into expressive speech using ElevenLabs text-to-speech.
MDGrey33Speak markdown, files, or inline text aloud using Kokoro text-to-speech.
Clean1inesCapture architectural decisions as structured ADRs with context, alternatives, and rationale.
