> ## Documentation Index
> Fetch the complete documentation index at: https://docs.cartesia.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Text Normalization

> How written text becomes spoken text, and what to do when something reads out wrong.

Text normalization converts written forms into spoken forms: `7:00 PM` is spoken as "seven PM", and `(415) 555-1212` is read as a phone number rather than a twelve-digit string. It runs automatically on every TTS request before the model speaks.

You control it with the `normalization` field:

* `auto` (default) — Cartesia decides how dates, times, and numbers are read
* `off` — skip the normalizer
* a locale code such as `en-IN` — read dates and numbers the Indian English way. See [supported locales](/build-with-cartesia/tts-models/preview#languages-and-locales).

Locale codes work on Sonic 3.6 (`sonic-preview`). On Sonic 3.5 they return 400. English and Hindi currently read the same way — see [regional reading conventions](/build-with-cartesia/capability-guides/advanced-capabilities#regional-reading-conventions).

Most transcripts need no preparation. This page covers what the normalizer handles, its current limitations and their workarounds, and how to turn it off.

## What gets normalized

| Category      | Example input                                              | Status                                                                              |
| ------------- | ---------------------------------------------------------- | ----------------------------------------------------------------------------------- |
| Dates         | `04/20/2026`                                               | Common written forms are automatically normalized                                   |
| Times         | `7:00 PM`, `14:30`                                         | Common written forms are automatically normalized                                   |
| Phone numbers | `(415) 555-1212`                                           | Common written forms are automatically normalized                                   |
| Currency      | `$19.99`                                                   | Common written forms are automatically normalized                                   |
| Units         | `km`                                                       | Units with everyday usage are automatically normalized                              |
| Numbers       | `1,234,567`                                                | Common written forms are automatically normalized                                   |
| Date ranges   | `1999-2000`                                                | Not normalized — [write the range with "to"](#a-date-or-year-range-reads-out-wrong) |
| Fractions     | `2/3`                                                      | Not normalized — write them out ("two thirds")                                      |
| Other         | Equations, chemical compounds, uncommon units (e.g. V, Pa) | Not normalized — write them out ("volts, pascals")                                  |

**Normalized** categories are locale-aware and read according to the conventions of the request's language. **Common written forms** read correctly in the formats shown on [prompting tips](/build-with-cartesia/capability-guides/prompting-tips#recommendations); for unusual forms, [pre-normalize](/build-with-cartesia/capability-guides/prompting-tips#pre-normalization) as a fallback.

24-hour times are read as-is in the language's convention — `14:30` in an English transcript reads as "fourteen thirty".

## Known limitations

### A date or year range reads out wrong

Hyphenated ranges like `1999-2000` or `Dec 5-Dec 12` are not automatically normalized in any language. Write the range with "to" instead:

| Unreliable                       | Reliable                            |
| -------------------------------- | ----------------------------------- |
| `The war lasted from 1999-2000.` | `The war lasted from 1999 to 2000.` |
| `Open Dec 5-Dec 12.`             | `Open Dec 5 to Dec 12.`             |

### Industry-specific Terms

Some industries may have common abbreviations that are mutually understandable within that group (`PAX` = passengers for airlines). Because these abbreviations are not generally used, we recomend pre-normalizing these terms to ensure that they are spoken as expected.

### Abbreviations

Common patterns (`Dr. Smith`, `123 Main St`) generally read correctly. Less common titles, abbreviations, and address formats may not (e.g. `STE` — write the specific form out as it should be spoken, or use a [pronunciation dictionary](/build-with-cartesia/capability-guides/custom-pronunciations) for a recurring term.

## Turning normalization off

See [turning normalization off](/build-with-cartesia/capability-guides/advanced-capabilities#turning-normalization-off) in Advanced capabilities.

## Troubleshooting a read-out problem

1. **Right words, wrong sounds?** That's model pronunciation, not normalization. Use a [pronunciation dictionary](/build-with-cartesia/capability-guides/custom-pronunciations).
2. **A written form expands into the wrong words?** That's normalization. Rewrite the input in a form the normalizer handles — see [known limitations](#known-limitations) for the common cases, like writing ranges with "to".
3. **Still wrong?** Pre-normalize the transcript and [turn normalization off](#turning-normalization-off). This gives you full control of the spoken form.

For transcript-writing guidance, see [prompting tips](/build-with-cartesia/capability-guides/prompting-tips).