Skip to content

Voice bridge·

text → the voice persona's mouth (say/mute) from the text personastools/voice_bridge.py, 1 tool.

From the module docstring

Voice bridge — async text-input queue feeding the bidi voice agent.

tool does
voice_say Send a message to the voice agent so it speaks it out loud.

voice_say·

voice_say(text: str, importance: int = 1) -> dict

Send a message to the voice agent so it speaks it out loud.

Use this from any other persona (telegram, thinker, shell) to make the voice agent speak something to the user. The voice agent picks it up from a shared SQLite queue within ~2 seconds.

argument meaning
text What the voice agent should speak (or react to). Plain text.
importance 0=silent log, 1=normal info (default), 2=URGENT URGENT briefings are read immediately even mid-conversation.

Returns

dict with 'id' of the queued message and 'status'.

Examples

voice_say("hey, the user just said hi over telegram")
voice_say("CRITICAL: production is down", importance=2)
voice_say("just confirming: telegram message received", importance=1)

source: tools/voice_bridge.py:133