input.keyterms, set when you create or update it, or inline over the WebSocket via session.update.
Set key terms
Passkeyterms inside the input object:
| Field | Type | Required | Notes |
|---|---|---|---|
input.keyterms | string[] | null | No | Up to 100 transcription-bias strings. null or [] clears the boost. |
What to add
- Brand, product, and feature names that aren’t in everyday English (
"AssemblyAI","Lemur","Ozempic"). - Proper nouns specific to this caller: their full name, their account holder’s name, the agent’s name if it’s unusual.
- Domain jargon that the model might otherwise transcribe as a common-word homophone (
"hemochromatosis","polysomnography"). - Acronyms you want spelled in full (
"PCI DSS","FedRAMP").
What NOT to add
- Common English words. Each entry boosts that string, and adding common words at the same weight as your rare terms dilutes the boost.
- Whole sentences or phrases. The boost is per-term, not per-phrase.
- Punctuation, formatting, or instructions. The list is treated as transcription hints, not as prompt context.
Update the list
Replace the list by sending a newkeyterms array. The new list takes effect on the next user utterance:
input.keyterms accepts up to 100 strings. Passing null or [] clears the boost. When configured inline via session.update, the list can also be replaced mid-session and takes effect on the next user utterance.