Suggest versions of a word to choose by ear

POST/assistants/{id}/pronunciations/suggest

Hears how the word must sound (a recording of someone saying it, or sounds_like), writes up to five ways to spell it for the assistant's voice, the word as written first, and returns each one said by that voice in sentence.

Request

curl -X POST "https://www.getrevox.com/api/assistants/3f6c2a1e-8b4d-4c7a-9e2f-5d1b7a9c0e34/pronunciations/suggest" \
  -H "Authorization: Bearer $REVOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "term": "Swile",
    "sentence": "Je vous appelle de la part de Swile.",
    "audio_base64": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YQAAAAA=",
    "mime_type": "audio/wav"
  }'

const res = await fetch("https://www.getrevox.com/api/assistants/3f6c2a1e-8b4d-4c7a-9e2f-5d1b7a9c0e34/pronunciations/suggest", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.REVOX_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    term: "Swile",
    sentence: "Je vous appelle de la part de Swile.",
    audio_base64: "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YQAAAAA=",
    mime_type: "audio/wav",
  }),
});
const data = await res.json();
console.log(data);

import os

import requests

response = requests.post(
    "https://www.getrevox.com/api/assistants/3f6c2a1e-8b4d-4c7a-9e2f-5d1b7a9c0e34/pronunciations/suggest",
    headers={"Authorization": f"Bearer {os.environ['REVOX_API_KEY']}"},
    json={
        "term": "Swile",
        "sentence": "Je vous appelle de la part de Swile.",
        "audio_base64": "UklGRiQAAABXQVZFZm10IBAAAAABAAEAQB8AAIA+AAACABAAZGF0YQAAAAA=",
        "mime_type": "audio/wav",
    },
    timeout=30,
)
response.raise_for_status()
print(response.json())

curl -X POST "https://www.getrevox.com/api/assistants/3f6c2a1e-8b4d-4c7a-9e2f-5d1b7a9c0e34/pronunciations/suggest" \
  -H "Authorization: Bearer $REVOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "term": "Lefebvre",
    "sentence": "Vous avez rendez-vous avec Maître Lefebvre.",
    "sounds_like": "le-fèvre, le b est muet"
  }'

const res = await fetch("https://www.getrevox.com/api/assistants/3f6c2a1e-8b4d-4c7a-9e2f-5d1b7a9c0e34/pronunciations/suggest", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.REVOX_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    term: "Lefebvre",
    sentence: "Vous avez rendez-vous avec Maître Lefebvre.",
    sounds_like: "le-fèvre, le b est muet",
  }),
});
const data = await res.json();
console.log(data);

import os

import requests

response = requests.post(
    "https://www.getrevox.com/api/assistants/3f6c2a1e-8b4d-4c7a-9e2f-5d1b7a9c0e34/pronunciations/suggest",
    headers={"Authorization": f"Bearer {os.environ['REVOX_API_KEY']}"},
    json={
        "term": "Lefebvre",
        "sentence": "Vous avez rendez-vous avec Maître Lefebvre.",
        "sounds_like": "le-fèvre, le b est muet",
    },
    timeout=30,
)
response.raise_for_status()
print(response.json())

audio_base64 is the recording (shortened here): someone saying the word the way the voice must say it.

Try itSend this request live

Response

Success

{
  "sounds_like": "swaïle, une seule syllabe, à l'anglaise",
  "versions": [
    {
      "text": "Hello, this is Julie from Acme.",
      "audio_base64": "audio base64"
    }
  ]
}

{
  "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
sentencestring
A sentence holding the word, as the assistant says it (e.g. the prompt's sentence that mentions it), to hear each version in context. Defaults to the word alone.
at most 300 characters
audio_base64string
A recording of someone saying the word the way the voice must say it, base64-encoded without a data: prefix. A few seconds is enough. Send it with mime_type, or send sounds_like instead.
1 to 3000000 characters
mime_typeenum (5 values)
Format of the recording.
Possible values"audio/wav""audio/mpeg""audio/ogg""audio/flac""audio/aac"
sounds_likestring
How it must sound, typed instead of a recording: 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

Response

200

sounds_likestring
How the word must sound, from the recording or as sent. Send it back to POST /assistants/{id}/pronunciations.
Example "swaïle, une seule syllabe, à l'anglaise"1 to 300 characters
versionsarray of object
Up to 5 ways to write the word for the assistant's voice, each with its audio, to listen to and choose from.

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.