> ## 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

> Control how written text becomes spoken text, and debugging tips.

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. By default, it runs on every TTS request before the model speaks.

You control it with the `normalization` field:

* `auto` (default) — use the reading conventions for the request's `language` or `locale`
* `off` — skip the normalizer
* a language or locale code such as `en` or `en-IN` — use that language's or region's reading conventions. See [supported locales](/build-with-cartesia/capability-guides/advanced-capabilities#which-locales-are-supported).

Most transcripts need no preparation. This page covers what the normalizer handles, 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. 24-hour times are read as-is in the language's convention (e.g. "fourteen thirty") |
| 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 use the conventions of the request's `language` or `locale`. **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.

## 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.`             |
| `$10-15`                         | `10 to 15 dollars`                  |

### 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 recommend 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?** Use a [pronunciation dictionary](/build-with-cartesia/capability-guides/custom-pronunciations).
2. **A written form expands into the wrong words?** Rewrite the input in a form the normalizer handles or pre-normalize the transcript.
3. **Still wrong?** Pre-normalize the transcript and [turn normalization off](/build-with-cartesia/capability-guides/advanced-capabilities#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).

## Normalizer worked examples

### Pre-normalized text with the normalizer off

For "teleprompter" transcripts you've already written out the way they should be spoken, custom symbol read-outs, or all-caps words that should be spoken as words:

```json theme={null}
{
  "model_id": "sonic-3.6",
  "transcript": "Your total is nineteen dollars and ninety-nine cents.",
  "voice": "a0e99841-438c-4a64-b679-ae501e7d6091",
  "locale": "en",
  "normalization": "off",
  "output_format": { "container": "mp3", "sample_rate": 44100, "bit_rate": 128000 }
}
```

Only the automatic normalizer is skipped — see [turning normalization off](#turning-normalization-off) for exactly what still applies.

### British accent with US reading conventions

This example uses Gemma, a British-accented voice, and changes the reading conventions with `normalization`.

```json theme={null}
{
  "model_id": "sonic-3.6",
  "transcript": "Your appointment is on 03/04/2026.",
  "voice": "62ae83ad-4f6a-430b-af41-a9bede9286ca",
  "locale": "en-GB",
  "normalization": "en-US",
  "output_format": { "container": "mp3", "sample_rate": 44100, "bit_rate": 128000 }
}
```

This reads with a British accent and US conventions (`03/04/2026` as March fourth).

### Different read-out conventions inside one transcript

If one clause needs Hindi read-outs and another needs English read-outs, split the transcript and send two requests with different `normalization` values and the **same voice**, so the accent stays consistent, then concatenate the audio on the client side:

```json Request 1 theme={null}
{
  "model_id": "sonic-3.6",
  "transcript": "Aapki appointment 15 tareekh ko hai.",
  "voice": "a0e99841-438c-4a64-b679-ae501e7d6091",
  "locale": "hi-IN",
  "normalization": "hi-IN",
  "output_format": { "container": "raw", "encoding": "pcm_s16le", "sample_rate": 44100 }
}
```

```json Request 2 theme={null}
{
  "model_id": "sonic-3.6",
  "transcript": "Please arrive by 2:30 PM on 08/15/2026.",
  "voice": "a0e99841-438c-4a64-b679-ae501e7d6091",
  "locale": "hi-IN",
  "normalization": "en-IN",
  "output_format": { "container": "raw", "encoding": "pcm_s16le", "sample_rate": 44100 }
}
```

On the [WebSocket API](/api-reference/tts/websocket), raw PCM chunks from consecutive generations can be concatenated directly.