- Word or phrase to be annotated. For example,
actually. - Phonetic alphabet to use.
ipaandcmuare supported, depending on the voice (see Voice support). - Phoneme with the pronunciation in the selected alphabet.
Voice support
Which phonetic alphabets you can use depends on the selected voice provider and its effective voice model. The dashboard shows the supported alphabets under Pronunciation in the agent’s speech settings. See supported languages by provider for voice-model language restrictions.
If an ElevenLabs voice uses Auto, an English-only agent resolves to Flash v2 and supports IPA and CMU. Agents that use other languages resolve to a newer ElevenLabs model that does not support pronunciation dictionaries. The dashboard displays the resulting support.
If the selected voice or voice model does not support pronunciation dictionaries, the Add button is hidden. Existing entries stay on the agent but do not affect the current voice. Switch to a supported voice or voice model to add entries or make existing entries take effect.
You can still edit an existing entry and change its alphabet while using an unsupported voice. The dialog warns that the entry does not affect the current voice.
How many entries can I add?
The pronunciation dictionary is a list on the agent — you can add multiple entries and there is no fixed cap enforced by the API. In practice:- Add one entry per word or short phrase you want to override. Each entry needs its own
word,alphabet, andphoneme. - Keep the dictionary focused on words the model actually mispronounces (uncommon proper nouns, brand names, technical terms, foreign words). Overriding common words can produce unnatural speech.
- Use a unique
wordvalue for each entry. The API rejects updates that contain duplicatewordvalues. - Very large dictionaries can push the agent payload close to request size limits when calling
update-agent. If you hit that, split entries across agents or trim rarely used words.

