Set how the voice says a word

PUT/assistants/{id}/pronunciations

Stores the version of a word the user chose by ear. On calls with the assistant's current voice, that text is sent to the voice in place of the word; the transcript keeps the word.

Request

curl -X PUT "https://www.getrevox.com/api/assistants/3f6c2a1e-8b4d-4c7a-9e2f-5d1b7a9c0e34/pronunciations" \
  -H "Authorization: Bearer $REVOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "term": "Swile",
    "sounds_like": "swaïle, une seule syllabe, à l'\''anglaise",
    "text": "Swaïle",
    "versions": ["Swile", "Swaïle", "Souaïle"]
  }'

const res = await fetch("https://www.getrevox.com/api/assistants/3f6c2a1e-8b4d-4c7a-9e2f-5d1b7a9c0e34/pronunciations", {
  method: "PUT",
  headers: {
    Authorization: `Bearer ${process.env.REVOX_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    term: "Swile",
    sounds_like: "swaïle, une seule syllabe, à l'anglaise",
    text: "Swaïle",
    versions: [
      "Swile",
      "Swaïle",
      "Souaïle",
    ],
  }),
});
const data = await res.json();
console.log(data);

import os

import requests

response = requests.put(
    "https://www.getrevox.com/api/assistants/3f6c2a1e-8b4d-4c7a-9e2f-5d1b7a9c0e34/pronunciations",
    headers={"Authorization": f"Bearer {os.environ['REVOX_API_KEY']}"},
    json={
        "term": "Swile",
        "sounds_like": "swaïle, une seule syllabe, à l'anglaise",
        "text": "Swaïle",
        "versions": [
            "Swile",
            "Swaïle",
            "Souaïle",
        ],
    },
    timeout=30,
)
response.raise_for_status()
print(response.json())

Try itSend this request live

Response

Success

{
  "pronunciation": {
    "id": "d4c3b2a1-9e8f-4a7b-8c6d-5e4f3a2b1c0d",
    "assistant_id": "3f6c2a1e-8b4d-4c7a-9e2f-5d1b7a9c0e34",
    "term": "Swile",
    "sounds_like": "swaïle, une seule syllabe, à l'anglaise",
    "replacement": "replacement",
    "versions": ["version"],
    "voice": {
      "provider": "cartesia",
      "id": "8e1f2a3b-4c5d-4e6f-9a0b-1c2d3e4f5a6b"
    },
    "voice_changed": false,
    "created_at": "2026-11-05T09:00:00Z",
    "updated_at": "2026-11-05T09:00:00Z"
  }
}

{
  "message": "Request validation failed",
  "bodyErrors": {
    "issues": [
      {
        "path": ["term"],
        "message": "Invalid input: expected string, received undefined",
        "code": "invalid_type"
      }
    ]
  }
}

{ "error": "Not found" }

Path parameters

idstringrequired
ID of the assistant, as returned by GET /assistants.

Request body

application/json

termstringrequired
The word or name as it is written in the prompt and as the assistant writes it, e.g. "Swile" or "Thibault Lhuillier". Matched whole-word and case-sensitively.
Example "Swile"1 to 100 characters
sounds_likestringrequired
How it must sound, as you would explain it to a colleague: a respelling in the call's language and any note on silent letters or English reading.
Example "swaïle, une seule syllabe, à l'anglaise"1 to 300 characters
textstringrequired
The version chosen, sent to the voice in place of the word on calls. The word itself means no replacement.
1 to 500 characters
versionsarray of string
Every version that was offered, kept to choose again later without a new recording.
Default []at most 10 items · each item 1 to 500 characters

Response

200

pronunciationobject

Errors

400Invalid request: a field or parameter failed validation{ "message"?: string, "error"?: string, "bodyErrors"?: {…} }
404Not found in your organization{ "message"?: string, "error"?: string, "bodyErrors"?: {…} }

Error bodies carry an error (or message) string; a 400 adds bodyErrors.issues. See Errors.