shy-article-62777
07/06/2025, 9:56 PMtall-airline-16756
07/06/2025, 9:56 PMtall-airline-16756
07/06/2025, 9:57 PMkeyterms
parameter, which is a list of key terms to improve recognition accuracy.
• Ensure you are using a Nova-3 model (models that start with "nova-3").
• Set the language to English ("en" or "en-US"), as keyterm prompting only works with English for Nova-3 models.
If you are using other models (Nova-2, Nova-1, Enhanced, or Base), you should use the Keywords feature instead of keyterms.
Sources: GitHub::livekit::agents | livekit-plugins/livekit-plugins-deepgram/livekit/...shy-article-62777
07/06/2025, 9:57 PMtall-airline-16756
07/06/2025, 9:57 PMshy-article-62777
07/06/2025, 9:57 PMtall-airline-16756
07/06/2025, 9:58 PMshy-article-62777
07/06/2025, 9:58 PMtall-airline-16756
07/06/2025, 9:58 PMfrom livekit.plugins.deepgram import STT
deepgram_stt = STT(
model="nova-2-general",
keywords=[("LiveKit", 1.5), ("YourKeyword", 2.0)],
# other parameters...
)
Here's the scoop on how this works:
• Each keyword is like a little booster pack in a tuple - you get the word and its boost value.
• Boost those keywords up with positive values to help them shine, or dial them down with negative values if you want them to take a step back.
• If you don't specify anything, it defaults to an empty list []
- totally optional!
Need any more help understanding this? I'm right here and happy to walk you through it! Just give me a shout. 😊 Sources: livekit.plugins.deepgram API documentation | Deepgram integration guide | LiveKit Docs