Keyterm Prompting
Keyterm Prompting allows you to improve Keyword Recall Rate (KRR) for important keyterms or phrases up to 90%.
Keyterm Prompting allows you to improve Keyword Recall Rate (KRR) for important keyterms or phrases up to 90%.
keyterm string
Instantly increase accuracy and recognition of up to 100 important terminology, product and company names, industry jargon, phrases and more.
Keyterm Prompting is available for both monolingual and multilingual transcription using the Nova-3 Models, as well as Flux. To boost recognition of keywords using another Deepgram model (such as Nova-2), use the Keywords feature.
To enable Keyterm Prompting, add a keyterm parameter in the query string and set it to your chosen key term:
keyterm=KEYTERM
To transcribe audio from a file on your computer, run the following cURL command in a terminal or your favorite API client.
Replace YOUR_DEEPGRAM_API_KEY with your Deepgram API Key.
The following examples demonstrate how keyterms can significantly improve recognition accuracy and confidence scores for industry-specific terminology. These examples show typical improvements you might see across Drive-Thru, IVR, call center, and medical transcription use cases.
The confidence scores below are illustrative examples showing typical improvement patterns. Actual results may vary based on audio quality, accent, and context.
When choosing keyterms, consider the following guidelines to maximize accuracy:
Good Keyterm Examples:
tretinoin, diagnosis), technical jargon (escalation, API)account number, customer service)Deepgram, iPhone, Dr. Smith)algorithm, protocol, refill)What to Avoid:
the, and, is)Keyterms preserve formatting (including case and punctuation) which can help control how proper nouns, product names, or company names are transcribed. The model will use both the keyterm formatting and the audio context to determine the final transcription format.
Best practices for keyterm formatting:
Deepgram, iPhone, Dr. Smith)tretinoin, algorithm, protocol)When smart formatting is applied to the transcript, words that start sentences may be automatically capitalized regardless of keyterm formatting.
Note that while the model was trained with formatted keyterms, the final transcription may not always exactly match the keyterm’s formatting. The model balances the keyterm information with the audio context when determining capitalization and punctuation in the output.
A space must be properly URL-encoded to ensure compatibility. Both %20 and + are valid encodings, but their usage depends on context. In URL paths, spaces must be encoded as %20, while in query parameters, either %20 or + can be used.
You can pass in multiple keywords in your query string in several ways:
Repeat the keyterm parameter for each keyterm to ensure each keyterm is processed individually.
Use an encoded space %20 to separate each keyterm and combine multiple keyterms into a single space-delimited value and boost an entire phrase as a cohesive unit.
Use a plus + to separate each keyterm and combine multiple keyterms into a single space-delimited value and boost an entire phrase as a cohesive unit.
Key Terms are limited to 500 tokens per request; anything beyond that will return an error like so:
When using Flux, you can update keyterms mid-stream using the Configure control message. This allows you to adapt keyterm lists as conversation context changes without reconnecting.
For example, update keyterms when transitioning from general conversation to product-specific discussions, or clear keyterms when they’re no longer relevant.