Text Normalization

Return normalized text exactly as the TTS model receives it before synthesis.

cURL

curl --request POST \
  --url https://optimize.rime.ai/textnorm \
  --header 'Accept: application/json' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --fail \
  --data '{
  "text": "<string>"
}'

200

{
  "normalized": "one two three four, one, eight hundred, four four four, four one four one"
}

All requests require authentication with a bearer token in the Authorization header: Authorization: Bearer YOUR_API_KEY. See API authentication for how to create a key.

Overview

This endpoint returns the normalized form of an input string exactly as Rime’s TTS models receive it before synthesis. Use it to inspect numbers, phone numbers, dates, and other non-standard words.

Use it to preview how a given input will be spoken, or to debug unexpected pronunciations of digits, sequences, and punctuation.

Defaults to English. Pass the lang field for other languages; see Languages for the full list. For details on what’s normalized natively, known gaps, and how to pre-normalize problematic patterns, see Text normalization.

Example

A request takes the string text and, optionally, a lang code:

curl -X POST https://optimize.rime.ai/textnorm \
     -H "Authorization: Bearer YOUR_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{"text":"1234 1,2,3,4 1-800-444-4141 "}'

The response includes the normalized string:

{"normalized":"one two three four, one , two , three , four, one, eight hundred, four four four, four one four one"}

To normalize text in a non-English language, pass a language code:

curl -X POST https://optimize.rime.ai/textnorm \
     -H "Authorization: Bearer $(rime key)" \
     -H "Content-Type: application/json" \
     -d '{"text":"Tengo 2 perros","lang":"es"}'

Variable parameters

text · string · required

The string you’d like to normalize. Numbers, phone numbers, and other non-standard words will be expanded into their spoken form.

lang · string

Language code (e.g. en, es, fr, de, and additional languages) selecting the normalization rules. Defaults to English when omitted.

cURL

curl --request POST \
  --url https://optimize.rime.ai/textnorm \
  --header 'Accept: application/json' \
  --header 'Authorization: Bearer YOUR_API_KEY' \
  --header 'Content-Type: application/json' \
  --fail \
  --data '{
  "text": "<string>"
}'

200

{
  "normalized": "one two three four, one, eight hundred, four four four, four one four one"
}