Overview
fal provides a hosted inference platform for a wide variety of model types, including Wizper, a speech-to-text model based on Whisper v3 Large. With LiveKit's fal integration and the Agents framework, you can build AI agents that integrate Wizper for fast and accurate transcription.
Quick reference
This section includes a basic usage example and some reference material. For links to more detailed documentation, see Additional resources.
Installation
Install the plugin from PyPI:
pip install "livekit-agents[fal]~=1.0"
Authentication
The fal plugin requires a fal API key.
Set FAL_KEY
in your .env
file.
Usage
Use fal STT in an AgentSession
or as a standalone transcription service. For example, you can use this STT in the Voice AI quickstart.
from livekit.plugins import falsession = AgentSession(stt = fal.STT(language="de",task="translate",),# ... llm, tts, etc.)
Parameters
This section describes some of the available parameters. See the plugin reference for a complete list of all available parameters.
Speech recognition language.
Task to perform with audio file. Valid values are transcribe
and translate
.
Additional resources
The following resources provide more information about using fal with LiveKit Agents.
Python package
The livekit-plugins-fal
package on PyPI.
Plugin reference
Reference for the fal STT plugin.
GitHub repo
View the source or contribute to the LiveKit fal STT plugin.
fal docs
fal's full docs site.
Voice AI quickstart
Get started with LiveKit Agents and fal.