Meta tags:
description= Boost STT accuracy for domain words and phrases;
Headings (most frequently used words):
and, keyterm, keyword, boosting, prompting, deepgram, keywords, enabling, in, vapi, why, use, important, notes, model, support, api, call, integration, example, of, post, request, format, intensifiers, phrases, best, practices, for, additional, resources, custom, voices,
Text of the page (most frequently used words):
the (32), for (22), #keywords (22), and (20), keyterm (19), call (19), custom (18), #deepgram (18), model (17), quickstart (17), keyword (16), boosting (14), vapi (14), assistant (12), voice (11), support (11), use (10), with (9), provider (9), prompting (9), phrases (9), you (8), openai (8), server (8), tool (8), calls (8), api (7), transcriber (7), words (7), number (7), speech (7), management (7), your (6), this (6), page (6), configuration (6), overview (6), tools (6), voices (5), uncommon (5), proper (5), nouns (5), models (5), intensifiers (5), single (5), example (5), compliance (5), data (5), new (5), web (5), phone (5), can (4), transcription (4), accuracy (4), reference (4), not (4), order (4), specifies (4), name (4), nova (4), post (4), request (4), integration (4), assistants (4), chat (4), examples (4), multilingual (4), scheduling (4), sms (4), streaming (4), sip (4), documentation (4), cli (4), specialized (3), resources (3), without (3), any (3), keyterms (3), best (3), practices (3), important (3), word (3), are (3), boost (3), recognition (3), apple (3), emma (3), what (3), azure (3), when (3), guide (3), plan (3), authentication (3), enterprise (3), google (3), testing (3), agents (3), rejection (3), triage (3), handoff (3), squads (3), widget (3), troubleshoot (3), errors (3), hooks (3), inbound (3), llms (3), built (2), following (2), guidelines (2), feature (2), enhanced (2), terminology (2), developers (2), com (2), docs (2), more (2), additional (2), extensive (2), consider (2), training (2), spelling (2), want (2), integer (2), increase (2), send (2), duplicates (2), improve (2), avoid (2), spaces (2), domain (2), terms (2), add (2), account (2), code (2), hipaa (2), recall (2), rate (2), multi (2), specified (2), snuffleupagus (2), that (2), suppress (2), likelihood (2), recognized (2), intensifier (2), values (2), accepted (2), format (2), speaks (2), first (2), firstmessagemode (2), firstmessage (2), language (2), formatting (2), pci (2), header (2), enabling (2), instead (2), available (2), base (2), text (2), need (2), vocabulary (2), notes (2), why (2), dashboard (2), status (2), website (2), consent (2), static (2), recording (2), how (2), cartesia (2), playht (2), elevenlabs (2), core (2), faq (2), ivr (2), navigation (2), environments (2), dev (2), uat (2), prod (2), debugging (2), boards (2), advanced (2), developing (2), locally (2), spam (2), events (2), setting (2), urls (2), webhooks (2), property (2), clinic (2), passing (2), between (2), lead (2), qualification (2), appointment (2), migrate (2), variable (2), substitution (2), session (2), compatibility (2), non (2), end (2), reasons (2), forwarding (2), transfer (2), voicemail (2), control (2), outbound (2), sdk (2), telnyx (2), twilio (2), telephony (2), free (2), agent (2), tts (2), knowledge (2), variables (2), fallback (2), background (2), messages (2), configurations (2), composer (2), guides (2), introduction (2), integrations (2), pre (2), release (2), sdks (2), mcp (2), index (2), level (2), txt (2), next, preferred, previous, edit, yes, was, helpful, these, effectively, utilize, within, ensuring, details, see, vocabularies, provide, capitalization, transcripts, correct, casing, minimal, boosts, reduce, false, positives, cautiously, moderate, each, once, don, results, focus, often, misses, begin, only, where, needed, start, small, confirmation, improves, krr, detect, reliably, unlike, plain, strings, kansas, suppressing, exponential, factors, being, default, higher, while, equivalent, specifying, negative, decimals, supported, schema, foo_bar, hello, world, forms, array, accepts, tokens, consisting, letters, digits, optional, after, colon, initial, message, will, speak, along, smart, both, conversational, capabilities, https, krieger, systrom, smartformat, true, voiceid, gpt, content, type, application, json, authorization, bearer, token, curl, create, enabled, make, enable, parameter, using, also, supply, most, effective, way, ensure, accurate, coverage, punctuation, should, frequently, quickly, updating, improving, trained, enhancing, beneficial, allows, transcriptions, leveraging, particularly, useful, dealing, providing, specific, enhance, quality, directly, through, stt, copy, scroll, top, light, tcpa, addresses, proxy, zero, retention, zdr, gdpr, jwt, sign, sso, flow, rss, feed, glossary, report, issues, sympana, connector, voiceaiwrapper, voicerr, vapify, chatdash, voiceflow, langfuse, supabase, cloudflare, gcp, cloud, storage, aws, assemblyai, talkscriber, soniox, speechmatics, gladia, openrouter, togetherai, perplexity, deepinfra, groq, gemini, anthropic, bedrock, inworld, rimeai, minimax, lmnt, legacy, migration, test, suites, silent, handoffs, routing, commerce, medical, retrieve, artifacts, analysis, concurrency, queue, debug, drops, hold, specialist, dynamic, transfers, based, warm, detection, customer, join, timeout, real, time, websocket, transport, trunk, credential, amazon, chime, plivo, zadarma, networking, firewall, trunking, escalation, calling, bring, own, fine, tuned, argument, encryption, query, retrieval, gohighlevel, slack, sheets, calendar, troubleshooting, aliases, client, side, keys, realtime, pipeline, email, address, reading, pronunciation, dictionaries, denoising, idle, flush, syntax, personalization, user, information, transient, permanent, legal, security, privacy, community, works, monitoring, scorecard, structured, outputs, simulations, evals, observability, workflows, campaigns, insights, place, numbers, conversation, behavior, concepts, get, started, ask, search, root, append, url, markdown, version,
Text of the page (random words):
deepgram keywords and keyterm prompting vapi for ai agents a documentation index is available at the root level at llms txt append llms txt to any url for a page level index or md for the markdown version of any page search ask ai website status support dashboard documentation api reference mcp sdks cli new what s new documentation api reference mcp sdks cli new what s new get started introduction phone calls web calls vapi guides composer pre release cli quickstart assistants quickstart core concepts conversation behavior model configurations tools custom keywords custom voices custom transcriber custom tts custom llms examples phone numbers free vapi number inbound sms telephony integrations sip integration phone number hooks calls place calls in call control call end reasons troubleshoot call errors call insights outbound campaigns quickstart overview chat quickstart streaming non streaming openai compatibility session management variable substitution sms chat web widget workflows migrate to squads quickstart overview examples squads quickstart overview handoff tool passing data between assistants examples webhooks setting server urls server events spam call rejection developing locally server authentication observability evals simulations pre release boards structured outputs scorecard monitoring best practices prompting guide debugging voice agents enterprise environments dev uat prod ivr navigation testing resources faq how vapi works integrations community support security and privacy legal introduction phone calls web calls vapi guides composer cli quickstart quickstart transient vs permanent configurations variables multilingual support personalization with user information voice formatting plan flush syntax background messages idle messages assistant hooks background speech denoising pronunciation dictionaries email address reading speech configuration voice pipeline configuration voice fallback configuration transcriber fallback configuration openai realtime speech to speech provider keys tools built in call tools voicemail tool custom tools code tool client side tools web sdk tool rejection plan static variables and aliases custom tools troubleshooting google calendar google sheets slack gohighlevel knowledge retrieval query tool custom knowledge base argument encryption custom keywords custom voices elevenlabs playht cartesia custom transcriber custom tts fine tuned openai models bring your own server tool calling integration appointment scheduling lead qualification inbound support voice widget documentation agent support escalation multilingual agent free vapi number inbound sms twilio telnyx sip telephony sip trunking networking and firewall twilio telnyx zadarma plivo amazon chime sdk troubleshoot sip trunk credential errors phone number hooks calls outbound calls websocket transport real time call control customer join timeout voicemail detection call forwarding assistant based warm transfer dynamic call transfers on hold specialist transfer debug forwarding drops call queue management call concurrency call end reasons troubleshoot call errors call analysis call recording retrieve call artifacts quickstart overview quickstart streaming non streaming openai compatibility session management variable substitution sms chat web widget migrate to squads quickstart overview appointment scheduling lead qualification medical triage order management property management multilingual support quickstart overview handoff tool passing data between assistants clinic triage scheduling handoff tool clinic triage scheduling e commerce order management property management routing multilingual support silent handoffs webhooks setting server urls server events spam call rejection developing locally server authentication quickstart advanced quickstart advanced boards quickstart examples quickstart quickstart prompting guide debugging voice agents enterprise environments dev uat prod ivr navigation test suites chat testing voice testing faq core models voices text to speech vapi voices legacy migration elevenlabs playht azure openai cartesia lmnt minimax rimeai deepgram inworld openai azure openai anthropic bedrock gemini groq deepinfra perplexity togetherai openrouter deepgram google gladia speechmatics soniox talkscriber assemblyai aws s3 gcp cloud storage cloudflare r2 supabase langfuse voiceflow chatdash vapify voicerr ai voiceaiwrapper sympana connector support how to report issues enterprise glossary rss feed data flow single sign on sso jwt authentication recording consent plan gdpr compliance hipaa compliance zero data retention zdr pci compliance proxy server guide static ip addresses tcpa consent guidelines website status support dashboard light on this page why use keyword boosting important notes model support enabling keyword boosting in vapi api call integration example of post request format and intensifiers keyterm prompting phrases best practices for keyword and keyterm boosting additional resources scroll to top assistants deepgram keywords and keyterm prompting copy page boost stt accuracy for domain words and phrases vapi allows you to improve the accuracy of your transcriptions by leveraging deepgram s keyword boosting feature this is particularly useful when dealing with specialized terminology or uncommon proper nouns by providing specific keywords to the deepgram model you can enhance transcription quality directly through vapi why use keyword boosting keyword boosting is beneficial for enhancing the recognition of specialized terms and proper nouns improving transcription accuracy without the need for a custom trained model quickly updating the model s vocabulary with new or uncommon words important notes keywords should be uncommon words or proper nouns not frequently recognized by the model use single words for keywords no spaces or punctuation for multi word phrases use keyterm instead custom model training is the most effective way to ensure accurate keyword recognition when you need extensive vocabulary coverage model support keywords is available on deepgram nova 2 nova 1 enhanced and base speech to text models for nova 3 models use keyterm prompting instead of keywords enabling keyword boosting in vapi api call integration to enable keyword boosting add the keywords parameter to your assistant s transcriber configuration when using the deepgram provider you can also supply keyterm to boost recall for phrases example of post request to create an assistant with keyword boosting enabled you can make the following post request to vapi curl request post header authorization bearer token header content type application json data name emma model model gpt 4o provider openai voice voiceid emma provider azure transcriber provider deepgram model nova 2 language en smartformat true keywords snuffleupagus 5 systrom krieger keyterm order number account id pci compliance firstmessage hi i am emma what is your name firstmessagemode assistant speaks first https api vapi ai assistant in this configuration name the name of the assistant model specifies the model and provider for the assistant s conversational capabilities voice specifies the voice and provider for the assistant s speech transcriber specifies deepgram as the transcription provider along with the model language smart formatting and both keywords single words and keyterm phrases for boosting firstmessage the initial message the assistant will speak firstmessagemode specifies that the assistant speaks first format and intensifiers the keywords array accepts single word tokens consisting of letters and digits with an optional integer intensifier after a colon accepted forms apple apple 3 apple 2 not accepted order number use keyterm hello world foo_bar rate 1 5 decimals are not supported by this schema intensifiers are exponential factors that boost or suppress the likelihood of the specified keyword being recognized the default intensifier is 1 higher values increase the likelihood while 0 is equivalent to not specifying a keyword negative values suppress recognition boosting example keywords snuffleupagus 5 suppressing example keywords kansas 10 keyterm prompting phrases deepgram s keyterm prompting improves keyword recall rate krr for important keyterms or phrases use keyterm for multi word phrases you want the model to detect more reliably unlike keywords keyterms are specified as plain strings without intensifiers example keyterm account number confirmation code hipaa compliance best practices for keyword and keyterm boosting start small begin without any boosting add keywords keyterms only where needed send uncommon words focus on proper nouns or domain terms the model often misses use keywords for single words keyterm for phrases avoid spaces in keywords avoid duplicates send each keyword once duplicates don t improve results moderate intensifiers use minimal integer boosts to reduce false positives increase cautiously correct spelling casing provide the spelling and capitalization you want in transcripts consider custom models for extensive vocabularies consider custom model training with deepgram additional resources for more details see deepgram keywords developers deepgram com docs keywords deepgram keyterm prompting developers deepgram com docs keyterm api reference deepgram transcriber keywords and keyterm in the api reference by following these guidelines you can effectively utilize deepgram s keyword boosting feature within your vapi assistant ensuring enhanced transcription accuracy for specialized terminology and uncommon proper nouns was this page helpful yes no edit this page previous custom voices use a custom voice with your preferred provider next built with
|
