Formatting

format_text lets you control how numbers and other entities in your transcript are formatted. By default, format_text is true, so numbers, dates, and similar entities are formatted for readability.

When format_text is set to false, the transcript reflects exactly what was said instead — a speaker saying “one hundred” comes back as “one hundred” rather than 100, useful for verbatim workflows, like medical dictation.

Python

To enable text formatting, set format_text to True in the POST request body:

import requests
import time

base_url = "https://api.assemblyai.com"
headers = {"authorization": "<YOUR_API_KEY>"}

data = {
    "audio_url": "https://assemblyaiassets.com/8e23e453-format_text.m4a",
    "language_detection": True,
    "format_text": True
}

response = requests.post(base_url + "/v2/transcript", headers=headers, json=data)

if response.status_code != 200:
    print(f"Error: {response.status_code}, Response: {response.text}")
    response.raise_for_status()

transcript_response = response.json()
transcript_id = transcript_response["id"]
polling_endpoint = f"{base_url}/v2/transcript/{transcript_id}"

while True:
    transcript = requests.get(polling_endpoint, headers=headers).json()
    if transcript["status"] == "completed":
        print(transcript["text"])
        break
    elif transcript["status"] == "error":
        raise RuntimeError(f"Transcription failed: {transcript['error']}")
    else:
        time.sleep(3)

Python SDK

To enable text formatting, set format_text to True in the transcription config.

from assemblyai.prerecorded.v2 import Transcriber, TranscriptionConfig

# You can use a local filepath:
# audio_file = "./example.mp3"

# Or use a publicly-accessible URL:
audio_file = "https://assemblyaiassets.com/8e23e453-format_text.m4a"

config = TranscriptionConfig(
    language_detection=True,
    format_text=True,
)

transcriber = Transcriber(api_key="<YOUR_API_KEY>")
transcript = transcriber.transcribe(audio_file, config)

print(transcript.text)

JavaScript

To enable text formatting, set format_text to true in the POST request body:

const baseUrl = "https://api.assemblyai.com";
const headers = {
  authorization: "<YOUR_API_KEY>",
};

const data = {
  audio_url: "https://assemblyaiassets.com/8e23e453-format_text.m4a",
  language_detection: true,
  format_text: true,
};

const url = `${baseUrl}/v2/transcript`;
let res = await fetch(url, {
  method: "POST",
  headers: { ...headers, "Content-Type": "application/json" },
  body: JSON.stringify(data),
});
if (!res.ok) throw new Error(`Error: ${res.status}`);
const response = await res.json();

const transcriptId = response.id;
const pollingEndpoint = `${baseUrl}/v2/transcript/${transcriptId}`;

while (true) {
  res = await fetch(pollingEndpoint, { headers });
  if (!res.ok) throw new Error(`Error: ${res.status}`);
  const transcriptionResult = await res.json();

  if (transcriptionResult.status === "completed") {
    console.log(transcriptionResult.text);
    break;
  } else if (transcriptionResult.status === "error") {
    throw new Error(`Transcription failed: ${transcriptionResult.error}`);
  } else {
    await new Promise((resolve) => setTimeout(resolve, 3000));
  }
}

JavaScript SDK

To enable text formatting, set format_text to true in the transcription config.

import { AssemblyAI } from "assemblyai";

const client = new AssemblyAI({
  apiKey: "<YOUR_API_KEY>",
});

// You can use a local filepath:
// const audioFile = "./example.mp3"

// Or use a publicly-accessible URL:
const audioFile = "https://assemblyaiassets.com/8e23e453-format_text.m4a";

const params = {
  audio: audioFile,
  language_detection: true,
  format_text: true,
};

const run = async () => {
  const transcript = await client.transcripts.transcribe(params);
  console.log(transcript.text);
};

run();

Supported languages

Unformatted output (format_text: false) is supported in the following languages:

Model	Supported languages
Universal-3.5 Pro	English, Spanish, German, French, Portuguese, Italian
Universal-2	English, Spanish, German