curl -X POST 'https://api.elevenlabs.io/v1/studio/projects/project-id/pronunciation-dictionaries' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "pronunciation_dictionary_locators": [
    {
      "pronunciation_dictionary_id": "string",
      "version_id": "string"
    }
  ],
  "invalidate_affected_text": true
}'

# POST /v1/studio/projects/{project_id}/pronunciation-dictionaries (ElevenLabs API)
Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03

> Create Pronunciation Dictionaries

## Critical Gotchas
* Authentication uses the non-standard `xi-api-key` header, not `Authorization: Bearer`. Sending a Bearer token returns HTTP 401.
* Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (`--output speech.mp3`) rather than parsing it.

## cURL
curl -X POST 'https://api.elevenlabs.io/v1/studio/projects/project-id/pronunciation-dictionaries' \
  -H "xi-api-key: $ELEVENLABS_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"pronunciation_dictionary_locators":[{}],"invalidate_affected_text":true}'

## Parameters
| Name | In | Type | Required | Description |
| :--- | :--- | :--- | :--- | :--- |
| project_id | path | string | Yes | The ID of the Studio project. |
| pronunciation_dictionary_locators | body | object[] | Yes | A list of pronunciation dictionary locators (pronunciatio... |
| invalidate_affected_text | body | boolean | No | This will automatically mark text in this project for rec... |

## Response (200 OK)
{"status":"ok"}

---
Need an API key? Get one at https://elevenlabs.io/app/sign-up

POST

/v1/studio/projects/{project_id}/pronunciation-dictionaries

ElevenLabs API

Create Pronunciation Dictionaries

Base URL: https://api.elevenlabs.io
Auth: xi-api-key: <ELEVENLABS_API_KEY>
Last verified: 2026-09-03 · upstream hash matched

Actions

Agents: curl -H "Accept: text/markdown" this URL
→ 218 tokens · Vary: Accept

Critical gotchas

Authentication uses the non-standard xi-api-key header, not Authorization: Bearer. Sending a Bearer token returns HTTP 401.

Text-to-speech responses are raw binary audio, not JSON. Write the body to a file (--output speech.mp3) rather than parsing it.

cURL

curl -X POST 'https://api.elevenlabs.io/v1/studio/projects/project-id/pronunciation-dictionaries' \  -H "xi-api-key: $ELEVENLABS_API_KEY" \  -H 'Content-Type: application/json' \  -d '{  "pronunciation_dictionary_locators": [    {      "pronunciation_dictionary_id": "string",      "version_id": "string"    }  ],  "invalidate_affected_text": true}'

Get a free ElevenLabs API key → sponsored

Parameters

Name	In	Type	Required	Description
project_id	path	string	Yes	The ID of the Studio project.
pronunciation_dictionary_locators	body	object[]	Yes	A list of pronunciation dictionary locators (pronunciation_dictionary_id, version_id) encoded as a list of JSON strings for pronunciation dictionaries to be applied to the text. A list of json encoded strings is required as adding projects may occur through formData as opposed to jsonBody. To specify multiple dictionaries use multiple --form lines in your curl, such as --form 'pronunciation_dictionary_locators="{\"pronunciation_dictionary_id\":\"Vmd4Zor6fplcA7WrINey\",\"version_id\":\"hRPaxjlTdR7wFMhV4w0b\"}"' --form 'pronunciation_dictionary_locators="{\"pronunciation_dictionary_id\":\"JzWtcGQMJ6bnlWwyMo7e\",\"version_id\":\"lbmwxiLu4q6txYxgdZqn\"}"'.
invalidate_affected_text	body	boolean	No	This will automatically mark text in this project for reconversion when the new dictionary applies or the old one no longer does.

Response 200 OK

{
  "status": "ok"
}