Pronunciation & IPA

When the model mispronounces a brand name, product, or domain term, you have two tools: write IPA directly in the request text, or set up a pronunciation dictionary that fixes the word in every request.

Inline IPA in the request text

Write the IPA transcription between slashes, directly where the word would be:

"Willkommen bei /ˈkuːɡl̩/ Audio."

Use the slash form shown here and test it with the target voice and language. If normalization changes a specialized transcription, disable normalization for that request.

Python
JavaScript
cURL

audio = client.tts.generate(
    text="Willkommen bei /ˈkuːɡl̩/ Audio.",
    voice_id=1071,
    language="de",
)

const audio = await client.tts.generate({
  text: 'Willkommen bei /ˈkuːɡl̩/ Audio.',
  voiceId: 1071,
  language: 'de',
});

curl -X POST https://api.kugelaudio.com/v1/tts/generate \
  -H "Authorization: Bearer $KUGELAUDIO_API_KEY" \
  -H "Content-Type: application/json; charset=utf-8" \
  -d '{
    "text": "Willkommen bei /ˈkuːɡl̩/ Audio.",
    "voice_id": 1071,
    "language": "de"
  }' --output output.pcm

Use real IPA characters (the non-ASCII phonetic alphabet, e.g. ˈ, ː, ɡ), not ASCII respellings, inside the slashes. A plain English word between slashes is just read as text. SSML <phoneme> tags are not supported — write the IPA inline instead.

Inline IPA is per-request. If the same word needs fixing everywhere, put it in a dictionary instead:

Pronunciation dictionaries

A dictionary is a per-project word list applied automatically to every request. Each entry maps a word to either:

a replacement spelling (write it how it sounds), or
an IPA transcription (exact phonetic control).

When both are set, IPA wins.

{
  "word": "Kugel",
  "replacement": "Koogel",
  "ipa": "ˈkuːɡl̩"
}

Dictionaries are managed via the API or SDKs and applied server-side — your request text stays clean, and the fix applies to every request that uses the dictionary. Full management guide: Dictionaries · API reference · SDK pages: Python, JavaScript, Java.

Choosing the right tool

Problem	Tool
Word pronounced wrong everywhere (“Kugel” read as English)	Dictionary entry with `replacement` or `ipa`
Exact phonetics required (clinical terms, names)	Dictionary entry with `ipa`, or inline `/aɪ piː eɪ/`
One-off pronunciation fix in a single request	Inline IPA, or just write the spoken form (“Koogel Audio”)
Text should be spelled character-by-character (codes, emails)	`<spell>` tags
Numbers/dates/currency read wrong	Set `language` + normalization
Migrating from SSML `<phoneme alphabet="ipa">`	Remove the unsupported tag and replace it with inline `/…/` IPA

Quick example

Send the dictionary’s project ID on synthesis. With projectId set, active dictionaries apply automatically; use dictionaryIds when you need an exact selection:

const d = await client.dictionaries.create({ name: 'brand-terms', language: 'de' });
await client.dictionaries.entries.add(d.id, {
  word: 'Kugel',
  ipa: 'ˈkuːɡl̩',
});

const audio = await client.tts.generate({
  text: 'Willkommen bei Kugel Audio.',
  voiceId: 1071,
  language: 'de',
  projectId: d.projectId,
});

See Dictionaries for matching rules, case sensitivity, and bulk sync.

Get started

Build a voice agent

Generate audio

Voices

Deploy

SDK Reference

API Reference

Inline IPA in the request text

Pronunciation dictionaries

Choosing the right tool

Quick example

​Inline IPA in the request text

​Pronunciation dictionaries

​Choosing the right tool

​Quick example

Inline IPA in the request text

Pronunciation dictionaries

Choosing the right tool

Quick example