Skip to main content
Mistral AI is a speech-to-text plugin. It transcribes the caller’s audio with Mistral’s Voxtral realtime model, which detects the language automatically or can be pinned to one.

Setup

Set your Mistral AI API key in the worker environment. Generate a key from the Mistral console:
The variable is MISTRALAI_API_KEY, not the MISTRAL_API_KEY that Mistral’s own SDK reads.

Usage

Import the plugin and pass it to the pipeline’s stt slot.
Mistral settles a transcript only when the session ends. Include a VAD in the pipeline so it ends at the end of speech, or set turn_detection to let Mistral end turns itself.

Parameters

Constructor parameters for MistralAISTT. The Python and Node JS SDKs share these field names.

turn_detection keys

turn_detection takes a MistralAITurnDetectionConfig or a plain dict with the same keys.

Import paths

Transcribed text passes to the LLM once turn detection decides the caller has finished speaking.