Find & Replace

// // find & replace find & replace in elevateai echo real time transcription (rtt) enables automatic word substitution during transaction processing this feature improves transcription accuracy and consistency by correcting recurring misrecognitions and/or enforcing standardized spelling across brands, products, and domains a find & replace pair consists of a find term and a corresponding replace term during real time transcription, every instance of the find term is replaced with the specified replace term // // use find & replace to ensure consistent capitalization and spelling for brand names and trademarks correct words that the transcription engine often misidentifies standardize use of internal terminology or abbreviations example uses of find & replace true 220,220,221 unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type // // things to keep in mind limitations & behaviors the replace term is inserted exactly as entered, including capitalization pairs are processed in list order, from top to bottom duplicate find terms are not allowed, but duplicate replace terms are supported a blank replace term field will redact the find term from the final transcript, by replacing the selected find term with the \<blank> replace term each api token supports up to 100 find & replace pairs per language each token may have multiple language lists, but only one list per language the phrase limit counter updates automatically as pairs are added and removed find & replace lists are tied to the api token used when connecting to the api providing descriptive names to your api tokens will make managing multiple tokens and their associated lists much simpler across your team or enterprise note when the 100 pair find & replace limit is reached, existing entries must be deleted before adding new ones // // using find & replace 1\ manage at the api token level find & replace lists are attached to specific api tokens, allowing token level customization for example, your customer support token might include different substitutions than your sales token 2\ access the phrase editor log into the elevateai portal < app elevateai com > your security level within your account determines your access to the boosted phrases list access level by role true 330,331 unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type unhandled content type navigate to manage api tokens locate the desired token and select edit phrases to open the phrase editor ui only account owners or admin can edit a find & replace pair use the phrase editor to define and edit your find & replace pairs 3\ select a language choose the language you wish to edit from the dropdown each api token supports one find & replace list per language note a dot next to a language indicates that there is an existing find & replace list 4\ add or edit pairs click add find & replace to create a new entry, then enter your find & replace terms click save to attach the updated list to the token the limit counter will update when you add a new find & replace pair you can add up to 100 find & replace pairs to be processed during transcription 5\ delete or copy pairs to delete a find & replace pair, click the trash icon beside the entry to copy a find & replace pair, select copy from to duplicate a list from another token copied lists must be in the same language as the original token note when coping a list from one token to another, duplicated find & replace term pairs are ignored and will not be copied over coping a list could result in the limit being exceeded lists exceeding the limit must be reduced before saving elevateai will return a list of tokens, allowing you to select the list of find & replace pairs you want to copy from a dot next to a language indicates that there is an existing find & replace pair set on that token 6\ disabling find & replace to transcribe without find & replace , use a token that does not have an associated list to remove the find & replace feature completely, delete or disassociate the list in the portal // // best practices use descriptive token names to simplify multi list management keep lists concise to minimize performance overhead use version control across your lists before making major edits test results regularly to validate accuracy improvements pro tip use find & replace sparingly, for critical terms overuse of find & replace may cause unintended substitutions need more help? contact the mailto\ support\@elevateai com