Skip to main content
Most applications shouldn’t pre-normalize. Rime handles common patterns — currency with symbols, dates with years, clock times, phone numbers, standard measurements, and most numeric formats — natively. Pre-normalizing adds latency and engineering complexity for behavior you usually get for free. Before adding a pre-processing layer, review the formats Rime handles natively and verify any specific input with the /textnorm endpoint.
If you’ve reviewed the native handling and still need to pre-normalize specific patterns, this page documents the known gaps and provides a prompt template you can drop into the layer that generates your text.

When pre-normalizing makes sense

There are two cases where pre-normalization in your application is worth the cost:
  1. The input falls into a known gap. A small set of patterns aren’t reliably expanded today. Pre-expanding those specific patterns is the reliable fix.
  2. You need guaranteed consistency across regenerations. For utterances that must read identically every time — regulatory disclosures, legal read-backs, confirmation flows — pre-normalizing removes a source of variability.
For everything else, the right default is: trust Rime’s normalizer, and use /textnorm to verify anything that sounds off. If you find a pattern Rime doesn’t handle, flag it to Rime — fixes ship on Rime’s side instead of in every customer’s pre-processing layer.

Known gaps

These patterns aren’t reliably expanded today. Either avoid them at the source, or pre-expand them in the layer that generates your text.

Dates

  • Month-and-year only (07/2025). Reads as a literal slash-separated number. Expand to July 2025 in prose form.
  • MM/DD without a year (04/21). Expand to April 21st or April twenty-first.
  • Centuries and financial periods (21st century, 1H 2024, Q1 2025, 1Q, 2Q). Not consistently expanded.
  • Cross-month date ranges (May-June 2024). Not a recognized pattern.
  • Decade names. 1990s currently reads as “nineteen hundreds,” not “nineteen nineties.” Use the nineteen nineties or 1990's cautiously.

Times

  • Bare hour with meridiem (3pm or 3 pm). Less reliable than 3:00pm. Prefer the full form with minutes when precision matters.
  • European 15h30 times. The h separator isn’t recognized. Use 15:30.
  • Suffixed approximations. 9:00-ish reads the colon literally. Avoid or pre-normalize.

Numbers

  • Very long comma-separated numbers (10,000,000) sometimes fall back to digit-by-digit. Drop the commas (10000000) or use shorthand (10M).
  • Superscript exponents (10⁶) aren’t recognized. Use 1e6 or 10^6.
  • Very large ordinals (1,000,000th) fall back to digit-by-digit. Prefer writing out (one millionth).

Money

  • Scale-word ordering with non-dollar currencies (€900K can read as “nine hundred euros thousand”). Spell out: 900 thousand euros.
  • Country-plus-symbol prefixes (US$3B, HK$1,152,415, AUD$900K) aren’t always fully verbalized.
  • Negative amounts (-$50, −€100) aren’t well-tested. Prefer minus fifty dollars.

Measurements

  • m ambiguity (meter vs. million). 7m/s may read as “seven million per second.” Prefer 7 m/s with a space, or spell out the unit.
  • Technical / electrical units (kWh, A, V, J) sometimes pass through unexpanded. Spell out (6 kilowatt-hours) if verbalization matters.
  • Uncommon units (qt, btu, psi, dyne, ) are not reliably expanded.
  • Parenthesized compound units (5(kg/m²)) aren’t a recognized form.

Ranges

  • Inconsistent connector. Hyphen ranges are usually read as “to,” but in some contexts the hyphen is read literally. If consistency matters, use the word “to” directly.

Roman numerals

  • Isolated Roman numerals without a context word pass through unchanged. Use spell() to force letter-by-letter, or write out the number.
  • Mixed-format numbering (section 2.IV.3) isn’t handled.

Phone numbers

  • Vanity numbers (1-800-FLOWERS) keep the letters as a literal string. Use spell(FLOWERS) if you need letter-by-letter.
  • Extensions (555-1234 ext. 567, 555-1234 x 567) aren’t explicitly handled.

Miscellaneous

  • Context-dependent abbreviations (Dr., Mr., St.) rely on context and may not always resolve as expected. See Abbreviations.
  • Repeating decimals (0.3̄, 0.(3)) aren’t recognized.
  • Internationalized domain names (non-ASCII in URLs) aren’t supported.

Pre-normalization prompt template

If your application uses an LLM to generate text before sending it to Rime, you can add the rules below to its system prompt or run them as a post-processing pass. The template targets only the known gaps — Rime’s normalizer handles the rest, so there’s no need to pre-expand everything.