TTS

AIfiredcore.ai.tts

Text to speech. Picks a model from any connected TTS provider (Fish Audio, ElevenLabs, xAI) the same way the LLM picks its model. A wired lang overrides the language knob for providers that take one (xAI); Fish and ElevenLabs detect the language themselves and ignore it.

Fired. It runs when an event or a value lands on trigger, and pulls its other inputs at that moment.

Inputs

Port	Type	Notes
trigger	event	Fires the node
text	text
lang	lang	Optional

Outputs

Port	Type	Notes
audio	audio
trigger	event

Knobs

Knob	Kind	Default	Notes
model	model	none	stays a knob (cannot become an input)

Models that ship with Boltjar

Boltjar ships a manifest for each of these models, and the picker lists them. Picking a model adds its own settings to the node as knobs, and each of those can become an input. Models explains manifests and how to add one.

Model	Id	Needs	Can
ElevenLabs Multilingual v2	elevenlabs/multilingual_v2	ELEVENLABS_API_KEY
Fish Audio (s2)	fish/s2	FISH_API_KEY
xAI TTS (Grok voices)	xai/tts	XAI_API_KEY

Example

Speaks text. Fire trigger with text wired, and audio carries the clip as a data: URL that a Preview plays; switch on its autoplay to hear every reply. The voice and the other settings come from the model: xAI has preset voices, Fish Audio takes a voice reference id, ElevenLabs a voice id. A Strip in front keeps markdown and emoji from being read out. Every TTS model needs its provider’s key.

More in AI

• Embed: Turn text into an embedding vector with the embed model you pick, the way the LLM picks its model.
• LLM: A chat / multimodal model.
• Rerank: Reorder candidates by how well each one answers the query, and keep the best.
• STT: Speech to text.
• Tool: A tool the LLM can call.
• Tool Args: Where a tool’s body starts.