Skip to content
Sponsor

STT

AIfiredcore.ai.stt

Speech to text. Picks a model from any connected STT provider (Fish Audio, ElevenLabs, xAI) the same way the LLM picks its model. lang carries the language the provider detected.

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

Port Type Notes
trigger event Fires the node
audio audio
Port Type Notes
text text
lang lang Optional
trigger event
Knob Kind Default Notes
model model none stays a knob (cannot become an input)

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 Scribe v2 elevenlabs/scribe_v2 ELEVENLABS_API_KEY
Fish Audio ASR fish/asr FISH_API_KEY
xAI STT (grok-voice-transcribe 2.0) xai/stt XAI_API_KEY

Transcribes a clip. Wire a data: audio value into audio, from an Audio node or an Audio Input, and fire trigger. text carries the words and lang the language the provider heard; wire lang into a TTS lang to answer in the same language with an xAI voice. Every STT model needs its provider’s key.

  • 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.
  • Tool: A tool the LLM can call.
  • Tool Args: Where a tool’s body starts.
  • TTS: Text to speech.