Skip to main content

Agents

Custom vocabulary

Teaching the recogniser your product and place names.

What custom vocabulary does

Speech recognition guesses words from sound. Names it has never seen get mapped to the nearest common word. "Ozempic" becomes "so simple." "DELT-450" becomes "dealt four fifty." Once the transcript is wrong, everything downstream is wrong: the LLM sees the wrong word, the reply is wrong, and post-call analysis extracts the wrong field.

Custom vocabulary is a list of words and phrases you hand the recogniser in advance. It biases the recogniser toward those strings when the audio is ambiguous. It does not force them and it does not teach the agent what they mean.

Where to set it

Dashboard, on the Finn itself: Identity → Custom Vocabulary. There is no API field for vocabulary in the documented endpoints, so this is a dashboard-only operation. See agents-identity for the other fields on that tab.

The field takes a list of strings:

["Acme", "FinnAI", "Ozempic", "DELT-450", "Doctor Patel"]

Vocabulary is part of the Finn's configuration, so it is versioned with the rest of it and rolls back with it. See agents-versioning.

What to put in it

CategoryExamplesWhy the recogniser fails without it
Brand namesAcme, FinnAI, RazorpayInvented spellings have no dictionary entry
Product SKUsDELT-450, XR-12Letter-digit mixes get split into words
Drug and clinical termsOzempicRare, and misheard as common words
Place namesLocal suburbs, streets, branch namesRegional names are outside the general model
Person namesDoctor PatelStaff names callers say every call
Regulatory termsAadhaar, PAN card, GSTRegion-specific, often absent from the base model

Include the form callers actually say. If callers say "Delt four fifty" rather than reading the hyphen, add both DELT-450 and Delt 450.

What to leave out

Keep the list short and specific. Every entry raises the chance the recogniser hears that entry where it was not said.

  • Do not add common words. Adding right or four makes the recogniser hallucinate them into ordinary speech.
  • Do not add whole sentences. The bias applies to short phrases; long strings rarely match.
  • Do not add every product in your catalogue. Add the ones callers actually name out loud.
  • Do not use it to teach facts. If the agent needs to know what DELT-450 is, that belongs in the knowledge base or the prompt (agents-prompting).

Language behaviour

Vocabulary entries accept words in any language, independent of the Finn's configured language. This matters when callers code-switch and drop an English brand name into a Hindi sentence. The entry is matched on sound, so a Hindi-language Finn still benefits from English brand entries.

Recognition quality sets the ceiling. Vocabulary improves borderline recognitions, it does not rescue a language whose base accuracy is poor. Tier 3 languages need clean audio before vocabulary helps at all. See agents-multilingual and agents-stt.

What will go wrong

SymptomLikely causeFix
Term still transcribed wrongCaller says it differently to how you spelled itAdd the spoken variant as a second entry
Ordinary words replaced by a vocabulary termList contains a short or common-sounding entryRemove that entry
Agent says the name wrong when speakingVocabulary affects recognition only, not speechFix pronunciation in TTS settings, see agents-tts
Fix did not take effect on a live callChanges apply to new calls onlyWait for in-flight calls to end
Term recognised in tests, missed on real callsPhone audio is worse than your test audioTest over a real call, not chat

Testing on chat will not exercise vocabulary at all. Chat has no audio and no recogniser, so the transcript is whatever you typed. Use Test on Call to check a vocabulary change. See agents-testing.

A working loop

  1. Run calls and read the transcripts in call-logs.
  2. Note the exact wrong string the recogniser produced, not the word you expected.
  3. Add the intended term to Custom Vocabulary. If the wrong string suggests a different pronunciation, add that spoken form too.
  4. Save, then place a test call over the phone and say the term twice.
  5. Check the transcript. If the term is still wrong after two attempts, the audio or the language tier is the constraint, not the vocabulary list.

Vocabulary is a tuning step, not a setup step. Ship the Finn, collect real transcripts, and add entries against errors you have actually seen.