speak

When the user wants spoken audio, run node .rulesync/scripts/speak.mjs. Spec: .rulesync/reference/speak.md. Output only (text → mp3). Do not record a mic. Do not transcribe.

whoami · voices · say --text T [--provider elevenlabs|openai] [--voice ID] [--out path] [--play].

Auth: ELEVENLABS_API_KEY or OPENAI_API_KEY or ~/.grunt/speak.json. Do not commit the key. Default voices: ElevenLabs George (JBFqnCBsd6RMkjVDRZzb), OpenAI coral.

If the CLI exits non-zero, print its message. Lines with setup: are for the user — show that command. Tell them to run node .rulesync/scripts/setup.mjs speak (or grunt setup) in their terminal. Do not dump JSON. Do not invent a key. Spec: .rulesync/reference/speak.md .rulesync/reference/setup.md.