Language selection

Steer Dictation transcription toward one or more languages with the language_codes field.

Pass language_codes in the config part to steer transcription toward a specific language. The field always takes a list, so use a single-element list such as ["es"] for monolingual audio, and several codes for multilingual or code-switching audio.

• Accepts ISO language codes in a list: ["es"], or ["en", "es"]
• Defaults to English (en) when omitted
• Applies to the transcript only. The rewrite in llm_response follows the language of the transcript unless your llm_instruction says otherwise.

Python SDK

import assemblyai as aai

aai.settings.api_key = "<YOUR_API_KEY>"

config = aai.DictationConfig(language_codes=["es"])

result = aai.DictationTranscriber().transcribe_live("clip.wav", config)
print(result.text)

Python

import json
import requests

config = {"language_codes": ["es"]}

with open("clip.wav", "rb") as f:
    audio = f.read()

response = requests.post(
    "https://dictation.assemblyai.com/v1/transcribe/live",
    headers={"Authorization": "<YOUR_API_KEY>"},
    files={
        "config": (None, json.dumps(config), "application/json"),
        "audio": ("clip.wav", audio, "audio/wav"),
    },
    timeout=90,
)
response.raise_for_status()
print(response.json()["text"])

JavaScript

import { readFileSync } from "fs";

const config = { language_codes: ["es"] };

const audio = readFileSync("clip.wav");
const form = new FormData();
form.append(
  "config",
  new Blob([JSON.stringify(config)], { type: "application/json" })
);
form.append("audio", new Blob([audio], { type: "audio/wav" }), "clip.wav");

const response = await fetch(
  "https://dictation.assemblyai.com/v1/transcribe/live",
  { method: "POST", headers: { Authorization: "<YOUR_API_KEY>" }, body: form }
);
console.log((await response.json()).text);

cURL

curl -X POST https://dictation.assemblyai.com/v1/transcribe/live \
  -H 'Authorization: <YOUR_API_KEY>' \
  -F 'config={"language_codes": ["es"]};type=application/json' \
  -F 'audio=@clip.wav;type=audio/wav'

Multilingual audio

Pass several codes when a single clip moves between languages, which is common in dictation from bilingual speakers:

{ "language_codes": ["en", "es"] }

List only the languages you actually expect. Extra codes give the model more ways to be wrong on ambiguous audio.

Supported languages

The endpoint accepts 32 codes. Anything outside this set is rejected with a 400 that lists the full set in its detail.

Code	Language	Code	Language
en	English	ko	Korean
es	Spanish	ca	Catalan
de	German	gl	Galician
fr	French	ru	Russian
it	Italian	ro	Romanian
pt	Portuguese	et	Estonian
tr	Turkish	fa	Persian
nl	Dutch	yue	Cantonese
sv	Swedish	af	Afrikaans
no	Norwegian	mr	Marathi
da	Danish	zu	Zulu
fi	Finnish	xh	Xhosa
hi	Hindi	nn	Norwegian Nynorsk
vi	Vietnamese	ar	Arabic
he	Hebrew	ja	Japanese
ur	Urdu	zh	Mandarin

Related features

• Prompting and keyterms steers the transcript within the chosen language.
• Transcript rewriting reshapes the transcript after it is written.