ConfigureVoice & language

Pronunciation dictionaries

Learn how to control how your AI agent pronounces specific words and phrases.

Overview

Pronunciation dictionaries allow you to customize how your AI agent pronounces specific words or phrases. This is particularly useful for:

  • Correcting pronunciation of names, places, or technical terms
  • Ensuring consistent pronunciation across conversations
  • Customizing regional pronunciation variations
Pronunciation dictionary settings under the Voice tab

Configuration

You can find the pronunciation dictionary settings under the Voice tab in your agent’s configuration.

Phoneme tags only work with the eleven_flash_v2 and eleven_turbo_v2 models. When used with other models, the tags are silently skipped and the default pronunciation is used.

Phoneme tags (IPA or CMU) only work for English. For other languages, use alias tags instead to substitute spellings or phrases that produce the pronunciation you need.

Dictionary file format

Pronunciation dictionaries use XML-based .pls files. Here’s an example structure:

1<?xml version="1.0" encoding="UTF-8"?>
2<lexicon version="1.0"
3      xmlns="http://www.w3.org/2005/01/pronunciation-lexicon"
4      xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
5      xsi:schemaLocation="http://www.w3.org/2005/01/pronunciation-lexicon
6        http://www.w3.org/TR/2007/CR-pronunciation-lexicon-20071212/pls.xsd"
7      alphabet="ipa" xml:lang="en-GB">
8  <lexeme>
9    <grapheme>Apple</grapheme>
10    <phoneme>ˈæpl̩</phoneme>
11  </lexeme>
12  <lexeme>
13    <grapheme>UN</grapheme>
14    <alias>United Nations</alias>
15  </lexeme>
16</lexicon>

Supported formats

We support two types of pronunciation notation:

  1. IPA (International Phonetic Alphabet)

    • More precise control over pronunciation
    • Requires knowledge of IPA symbols
    • Example: “nginx” as /ˈɛndʒɪnˈɛks/

  2. CMU (Carnegie Mellon University) Dictionary format

    • Simpler ASCII-based format
    • More accessible for English pronunciations
    • Example: “tomato” as “T AH M EY T OW”

You can use AI tools like Claude or ChatGPT to help generate IPA or CMU notations for specific words.

Best practices

  1. Case sensitivity: Create separate entries for capitalized and lowercase versions of words if needed
  2. Testing: Always test pronunciations with your chosen voice and model
  3. Maintenance: Keep your dictionary organized and documented
  4. Scope: Focus on words that are frequently mispronounced or critical to your use case

FAQ

Phoneme tags are supported on eleven_flash_v2 and eleven_turbo_v2. All other models skip the phoneme entry and fall back to their normal pronunciation. For non-English languages, rely on alias tags because phoneme tags only cover English pronunciations.

Yes, you can upload multiple dictionary files to handle different sets of pronunciations.

The model will use its default pronunciation rules for any words not specified in the dictionary.

Additional resources