Create a dictation

Transcribe audio, format raw text, or perform both operations in one multipart request.

POST/v1/enterprise/dictate

Authorization

X-API-KeyAPI key · headerrequired

Long-lived Enterprise API credential provisioned for trusted servers.

AuthorizationBearer token (mlg_ent_client) · headerrequired

Short-lived token for browser, mobile, or desktop clients.

Request body

requiredmultipart/form-data

sourcestringrequired

smart transcribes and formats; transcription returns raw speech-to-text; format processes raw_text without audio.

Allowed:smarttranscriptionformat

audiostring<binary>

Required for smart and transcription. M4A is recommended.

raw_textstring

Required when source is format.

contextstring

Situation-specific app, screen, document, or cursor context.

dictionarystring

Names, custom vocabulary, product terms, acronyms, or replacements.

extra_instructionsstring

Request-specific style, behavior, or formatting instructions.

languagestring

Language code such as en, es, or fr. Omit for automatic detection.

audio_durationnumber

Client-measured audio duration hint.

min 0

transcription_idstring

Client correlation ID. The server creates one when omitted.

app_versionstring

Client app version for diagnostics.

platformstring

Client platform, such as server, web, desktop, or mobile.

storeboolean

Explicitly opt into full request, response, and audio persistence.

default: false

Responses

200Dictation completed.

idstringrequired

Server or client-provided transcription ID.

textstringrequired

Formatted result, or normalized raw output when formatting is not requested.

raw_textstringrequired

Raw transcription before formatting.

400The request is invalid.

errorstring

codestring

request_idstring

401The credential is missing, invalid, expired, or revoked.

errorstring

codestring

request_idstring

403The request origin is not allowed.

errorstring

codestring

request_idstring

408The request was cancelled or timed out. The client may retry with backoff.

errorstring

codestring

request_idstring

413The audio upload exceeds the configured limit.

errorstring

codestring

request_idstring

429The API key request limit was exceeded.

errorstring

codestring

request_idstring

500An internal error occurred while processing the request.

errorstring

codestring

request_idstring

503Dictation processing is temporarily unavailable.

errorstring

codestring

request_idstring

504Dictation processing is temporarily unavailable.

errorstring

codestring

request_idstring

Request

curl -X POST "https://go.monologue.to/v1/enterprise/dictate" \
  -H "X-API-Key: YOUR_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -d '{
  "source": "smart",
  "audio": "<binary>",
  "language": "en",
  "platform": "server"
}'

const response = await fetch("https://go.monologue.to/v1/enterprise/dictate", {
  method: "POST",
  headers: {
    "X-API-Key": "YOUR_API_KEY",
    "Content-Type": "multipart/form-data"
  },
  body: JSON.stringify({
  "source": "smart",
  "audio": "<binary>",
  "language": "en",
  "platform": "server"
})
});

import requests

response = requests.post(
    "https://go.monologue.to/v1/enterprise/dictate",
    headers={
        "X-API-Key": "YOUR_API_KEY",
        "Content-Type": "multipart/form-data"
    },
    json={
  "source": "smart",
  "audio": "<binary>",
  "language": "en",
  "platform": "server"
},
)

Response

{
  "id": "string",
  "text": "string",
  "raw_text": "string"
}