Text Normalization

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.

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. 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

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; for unusual forms, pre-normalize 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:

​

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 for a recurring term.

​

Turning normalization off

See 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.
2. A written form expands into the wrong words? That’s normalization. Rewrite the input in a form the normalizer handles — see known limitations for the common cases, like writing ranges with “to”.
3. Still wrong? Pre-normalize the transcript and turn normalization off. This gives you full control of the spoken form.

For transcript-writing guidance, see prompting tips.