Speech-to-Text (STT)

Transcribe audio into text.

Converts audio input to text using a speech-to-text (STT) model. This enables transcription services, voice commands, and other voice-driven interactions.

POSThttps://api.aimlapi.com/stt

Body

application/json

model*string

urlstring

audioobject

custom_intentobject

custom_topicobject

custom_intent_modestring

custom_topic_modestring

detect_languageboolean

detect_entitiesboolean

detect_topicsboolean

diarizeboolean

dictationboolean

diarize_versionstring

extrastring

filler_wordsboolean

intentsboolean

keywordsstring

languagestring

measurementsboolean

multi_channelboolean

numeralsboolean

paragraphsboolean

profanity_filterboolean

punctuateboolean

searchstring

sentimentboolean

smart_formatboolean

summarizestring

tagarray of string

topicsboolean

utterancesboolean

utt_splitnumber

Response

201

Request

JavaScriptCurlPython

const response = await fetch('https://api.aimlapi.com/stt', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "model": "text"
    }),
});
const data = await response.json();