AI-generated summary
Genesys Cloud's dictionary management feature enables users to enhance transcription accuracy by adding organization-specific terms, names, acronyms, and industry language for proper recognition in transcripts. Users access this functionality through Admin > Quality > Dictionary Management or Menu > Conversation Intelligence > Speech and Text Analytics > Dictionary Management to view, add, edit, and delete dictionary terms.
When adding a term, users must specify the term (maximum), select a dialect, and optionally add up to 10 "sounds like" words for phonetic recognition. Users must include at least three example phrases (maximum 20 phrases) containing the term. For Genesys Native Voice Transcription, users can configure a "Display As" field (50 character limit) to control transcript appearance. For Extended Voice Transcription Services (EVTS) using Amazon Web Services (AWS) Transcribe, the "sounds like" and example phrases fields are unavailable; instead, users define display formatting through the "Display As" field.
Dictionary entries apply to specific transcription engines—either Genesys Native Voice Transcription or EVTS—and are tied to specific dialects. Technical constraints include: all entries are processed in lowercase, special characters and capitalization are not supported, and only standard alphanumeric characters (a–z, 0–9) are permitted. For EVTS entries specifically, numbers must be spelled out, hyphens and unsupported special characters are prohibited, acronyms require periods, and multi-word terms use spaces. Character support varies by language or dialect when using EVTS, with some languages not supporting uppercase letters.
Dictionary entries progress through status states—Pending, Active, Failed, or Invalid—indicating application success. Updates typically take effect within 15 minutes and apply to new interactions, though ongoing interactions may not immediately reflect changes. Access requires appropriate permissions: View, Add, Edit, and Delete permissions under Speech and Text Analytics > dictionaryterm. Entries are engine-specific and dialect-specific; they are not automatically migrated between transcription engines, requiring manual recreation of terms when switching engines. The system validates entries during creation or editing, generating errors when terms include unsupported characters, have invalid formatting, or use unsupported dialect or engine combinations