> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cartesia.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Keyterm Prompting

> Improve transcription accuracy for specific words and phrases

Keyterm prompting improves transcription accuracy for important terms and phrases by biasing the model toward transcribing them. It's most useful for important or uncommon words and phrases, such as domain-specific terminology, brand or product names, and rare or invented words.

Pass one or more terms with the `keyterm` query parameter when you open the WebSocket connection:

```text theme={null}
wss://api.cartesia.ai/stt/websocket?model=ink-2&encoding=pcm_s16le&sample_rate=16000&keyterm=Ink%202&keyterm=Cartesia
```

To pass multiple terms, repeat the `keyterm` parameter, one per term:

```text theme={null}
?keyterm=Cartesia&keyterm=Sonic&keyterm=Ink
```

For a multi-word phrase, keep it in a single `keyterm` value and encode spaces as `%20`:

```text theme={null}
?keyterm=Ink%202
```

You can pass up to **100 keyterms** per connection, up to a total of **1200 characters** across all keyterms.

<Note>
  Keyterms apply for the entire connection and are set only when you open it. You cannot add or change keyterms mid-stream.
</Note>

<Note>
  Keyterm prompting works on both the [Realtime STT](/api-reference/stt/websocket) and [Realtime STT (Auto)](/api-reference/stt/turns/websocket) endpoints.
</Note>

## Best practices

Consider the following to achieve the best results:

* Use keyterms for important or uncommon words and phrases, such as domain-specific terminology, brand or product names, and rare or invented words
* Avoid generic, common words like "the" or "and"
* Avoid using too many keyterms and prioritize the ones that matter most
* Use exact spelling and capitalization for each keyterm