UtilityKit

500+ fast, free tools. Most run in your browser only; Image & PDF tools upload files to the backend when you run them.

Words to Number Converter

Convert English number words (e.g. 'forty-two thousand' or 'three point five') back to numeric form.

About Words to Number Converter

The Words to Number Converter parses English number words and phrases back into their numeric equivalents. Type or paste text like 'forty-two thousand three hundred and twelve' and the tool returns 42312. It handles all standard integer constructions up to the trillions, common ordinals, decimal phrases ('three point five' → 3.5), and negative values ('negative twenty' → -20). This is useful when processing text data, cleaning transcriptions, handling voice-to-text output, or working with documents where amounts are written in words and need to be converted back to numeric form for calculation.

Why use Words to Number Converter

  • Parses standard English number words up to trillions.
  • Handles ordinals, decimals (point notation), and negative values.
  • Useful for processing voice-to-text transcriptions with number words.
  • 100% browser-based — no API call needed.
  • Handy for cleaning data scraped from court transcripts or formal documents.
  • Saves time when migrating legacy records that mix words and digits.

How to use Words to Number Converter

  1. Type or paste English number words into the input field.
  2. The numeric equivalent appears instantly.
  3. Click Copy to copy the numeric output.
  4. Supports multi-word phrases like 'one million two hundred thousand'.
  5. Paste an entire sentence — only the numeric portion will be converted, with non-number words flagged.
  6. Toggle case-sensitive mode if your input mixes capitalized and lowercase words intentionally.
  7. Use the result alongside the Number to Words tool to verify round-trip accuracy.

When to use Words to Number Converter

  • Converting transcribed speech or dictation containing number words to digits.
  • Parsing number words in imported documents before spreadsheet processing.
  • Testing or building NLP systems that handle number word extraction.
  • Checking that written check amounts correspond to the expected numeric value.
  • Preparing data for spreadsheet import where amounts were transcribed in words.
  • Verifying that voice-to-text output captures dictated numbers correctly.

Examples

Simple cardinal

Input: forty-two thousand

Output: 42000

Decimal phrase

Input: three point one four

Output: 3.14

Negative ordinal

Input: negative twenty-first

Output: -21

Long compound

Input: one million two hundred fifty thousand

Output: 1250000

Tips

  • Hyphens and 'and' are treated as connectors — both 'twenty-one' and 'twenty one' parse to 21.
  • Use 'point' for decimals: 'three point one four' → 3.14. Each digit after 'point' becomes a decimal place.
  • When parsing transcribed speech, pre-clean the text by removing filler words ('um', 'like') for cleaner output.
  • The parser is forgiving with case — uppercase, lowercase, and mixed all work the same.
  • For negative values use 'negative' or 'minus' as a prefix — both are recognized.
  • If your text has multiple numbers, parse them one at a time for clearer output and easier debugging.
  • Ordinals (first, second, twenty-first) are converted to their cardinal equivalent (1, 2, 21) for downstream calculations.

Frequently Asked Questions

What is the largest number it can parse?▾
The parser handles numbers up to 'nine hundred ninety-nine trillion' (999,999,999,999,999).
Does it handle British 'and' (e.g. 'one hundred and twenty')?▾
Yes. 'And' is ignored as a connector word during parsing, so both 'one hundred twenty' and 'one hundred and twenty' produce 120.
What about ordinals like 'first', 'second', 'twenty-first'?▾
Common ordinal words (first, second, third, ... twenty-first, etc.) are parsed to their ordinal number (1, 2, 3, ..., 21).
Does it handle 'point' for decimals?▾
Yes. 'Three point five' → 3.5. Each digit after 'point' is treated as a decimal place.
What if I enter invalid input?▾
Unrecognized words are flagged and the parsed portion is returned with a note about which part could not be parsed.
Does it match the accuracy of NLP libraries like spaCy or NLTK?▾
For standard English number phrases, yes. Specialized libraries handle more edge cases (e.g., 'a couple', 'half a dozen') which this tool does not interpret.
Can I parse 'thirty-one fifty' (military-style) numbers?▾
No — that style ('thirty-one fifty' = 3150) is not standard. Use 'three thousand one hundred fifty' instead.
Is text I paste stored or logged anywhere?▾
No. Parsing runs entirely in your browser. Court transcripts, medical notes, and other sensitive text never leave your device.

Explore the category

Number to Words Converter Convert any number to its English words representation — useful for checks, invoices, and formal documents. Roman Numeral Converter Convert integers to Roman numerals and Roman numerals back to integers with strict validation. Pluralizer & Singularizer Convert English nouns between their singular and plural forms using proper grammar rules including irregular words. Date Difference Days, months and years between two dates Unit Converter Convert length, weight, temperature and more Salary Calculator Convert salary between hourly, monthly, and yearly
How Random Number Generation Works in Computing Math.random() and /dev/urandom look similar but are fundamentally different. One is suitable for games, one for cryptography. Understanding Jan 2026 · 9 min Binary, Octal, and Hexadecimal: Number Systems Every Developer Needs Binary is not just for low-level programming — it shows up in bitmasks, permissions, color values, and network addresses. This guide makes n Feb 2026 · 9 min

Glossary

Cardinal number
A number used for counting: one, two, three. Cardinals indicate quantity.
Ordinal number
A number indicating position or rank: first, second, third. The parser converts these to their cardinal equivalents.
Compound number
A number formed by combining smaller numbers, like 'twenty-three' (20 + 3) or 'three hundred forty-five' (300 + 45).
Place-value words
Words like 'hundred', 'thousand', 'million' that multiply the preceding number rather than adding to it.
Connector word
Words like 'and' that join number components without contributing a value. The parser ignores connectors.
Short scale
The American numbering system: million = 10^6, billion = 10^9, trillion = 10^12. The default for this parser.
Tokenization
The first step of parsing: splitting input text into individual words for evaluation.
Decimal point keyword
The word 'point' (sometimes 'dot' in informal speech) used to indicate the decimal separator in spoken numbers.