add_pronunciation | SignalWire

Add a pronunciation rule that tells the TTS engine how to speak a specific word or phrase. Useful for brand names, acronyms, and technical terms that are commonly mispronounced by text-to-speech engines.

Parameters

replace

strRequired

The expression to match in the AI’s output text.

with_text

strRequired

The phonetic spelling or alternative text the TTS engine should speak instead.

ignore_case

boolDefaults to False

Whether to ignore case when matching the replace expression.

Returns

AgentBase — Returns self for method chaining.

Example

1 from signalwire import AgentBase
2 
3 agent = AgentBase(name="support", route="/support")
4 agent.set_prompt_text("You are a helpful assistant.")
5 agent.add_pronunciation("SQL", "sequel")
6 agent.add_pronunciation("SWAIG", "swig", ignore_case=True)
7 agent.serve()