Add a language configuration with voice settings. The agent uses these configurations to support multilingual conversations with appropriate TTS voices.
Language configurations map to the SWML ai.languages array.
See the SWML languages reference for the full specification.
The voice parameter supports three formats: a simple voice name, an explicit
engine/model via separate parameters, or a combined "engine.voice:model" string.
A language configuration object with the following fields:
Human-readable language name (e.g., "English", "French", "Spanish").
Language code (e.g., "en-US", "fr-FR", "es-MX").
TTS voice identifier. Accepts one of three formats:
"en-US-Neural2-F""elevenlabs.josh:eleven_turbo_v2_5"engine: "josh"Explicit TTS engine name (e.g., "elevenlabs", "rime").
Filler phrases keyed by category for this language.
Speech recognition model identifier.
Per-function filler phrases, keyed by function name then language code.
AgentBase — Returns this for method chaining.